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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and proper nouns within various contexts

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

    entity names and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.45
     חיצוניים
    -0.45
    ArrowToggle
    -0.45
    webElement
    -0.42
     كومونز
    -0.41
    InitVars
    -0.40
     <=",
    -0.38
    parsedMessage
    -0.37
     الحره
    -0.36
    ⓧ
    -0.36
    POSITIVE LOGITS
    省市镇
    0.54
     Biôgrafia
    0.48
    Réalisation
    0.47
    flä
    0.46
     pleaſure
    0.45
    Panamoan
    0.45
     Kort
    0.44
     ujarnya
    0.44
    ientras
    0.43
     PEND
    0.43
    Act Density 0.344%

    No Known Activations