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

    Neuronpedia

    INDEX
    Explanations

    sections of code that are involved with tracking or logging performance metrics

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

    HTML/XML structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.59
     Мексичка
    -0.54
    WebElementEntity
    -0.54
    httphttps
    -0.52
    ValueStyle
    -0.52
     ProtoMessage
    -0.52
    ksamkeit
    -0.52
     ویکی‌پدیا
    -0.50
    RUnlock
    -0.49
     disambiguazione
    -0.49
    POSITIVE LOGITS
     sínt
    0.38
    ものです
    0.36
    0.34
    0.32
    市镇
    0.32
     fin
    0.31
    Kanpo
    0.31
    0.31
    0.31
     flag
    0.31
    Act Density 0.026%

    No Known Activations