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

    Neuronpedia

    INDEX
    Explanations

    the presence of numerical values or references to numbered steps

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

    Enumerations or lists numbered starting with 3

    np_acts-logits-general · gemini-2.0-flash

    numbered lists ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.78
    %)$
    -0.75
    LOAT
    -0.67
    تقاوى
    -0.61
     <=",
    -0.59
     userManager
    -0.59
    참고
    -0.59
    disposing
    -0.58
    andle
    -0.57
    zda
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    0.73
    4
    0.64
    basicConfig
    0.56
     Quarte
    0.53
     @"/
    0.51
     Four
    0.51
     Fourth
    0.50
    Fourth
    0.49
    Four
    0.48
    viertel
    0.46
    Act Density 0.192%

    No Known Activations