Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of logarithmic or related mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "Log"

    np_acts-logits-general · gemini-2.0-flash

    Log transformations and related words

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "Log" or "log" appearing as a standalone token or at the beginning of phrases related to logging, login actions, or logarithmic operations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @kparkhamchuk
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.90
    tagHelperRunner
    -0.74
     EconPapers
    -0.69
    帖最后由
    -0.68
     disambiguazione
    -0.68
    StoryboardSegue
    -0.67
    Obrázky
    -0.67
     nakalista
    -0.67
     typelib
    -0.66
     continúas
    -0.62
    POSITIVE LOGITS
    Slf
    0.87
     logs
    0.86
     LOG
    0.84
    arithmic
    0.77
     Logs
    0.77
     log
    0.66
    cabin
    0.64
    getLog
    0.63
     Log
    0.61
    日志
    0.60
    Act Density 0.066%

    No Known Activations