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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and documentation formatting

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

    reference links with ref-type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.33
     suficientemente
    -0.27
     guste
    -0.27
    BagLayout
    -0.26
    Abitanti
    -0.25
     preguntó
    -0.25
     tanya
    -0.25
    透
    -0.24
    BeginContext
    -0.24
     levantó
    -0.24
    POSITIVE LOGITS
    int
    0.96
     int
    0.86
    OGND
    0.70
    хьтан
    0.70
    󠁣
    0.68
     autorytatywna
    0.66
    Географи
    0.61
     للمعارف
    0.61
     الرياضيه
    0.60
    HtmlAttribute
    0.59
    Act Density 0.001%

    No Known Activations