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

    Neuronpedia

    INDEX
    Explanations

    references to supplementary data and files

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

    table references and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.90
     мәкал
    -0.64
    RenderAtEndOf
    -0.64
     ब्रेकडाउन
    -0.64
    RTLR
    -0.63
    transQ
    -0.63
    TagMode
    -0.63
     noDo
    -0.62
     resourceCulture
    -0.62
    ⤹
    -0.58
    POSITIVE LOGITS
     çıktı
    0.41
     detailed
    0.40
     dibujos
    0.37
     מלא
    0.36
    Jeografia
    0.35
    faßt
    0.35
     mélang
    0.35
    licted
    0.35
    Litteratur
    0.35
    โ
    0.35
    Act Density 0.302%

    No Known Activations