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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and preferences

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

    first person perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.47
    曖昧さ回避
    -0.47
    Pranala
    -0.47
    Архівовано
    -0.47
     uitzicht
    -0.46
    ListView
    -0.45
     مشين
    -0.44
    זיה
    -0.43
     isNameExpr
    -0.42
    ulaski
    -0.42
    POSITIVE LOGITS
     myself
    0.53
     '\\;'
    0.43
     unknownFields
    0.43
    ReusableCell
    0.43
     wireType
    0.41
    myself
    0.40
    AntiForgeryToken
    0.40
     myſelf
    0.39
    RTEX
    0.39
    tidaknya
    0.38
    Act Density 0.045%

    No Known Activations