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

    Neuronpedia

    INDEX
    Explanations

    sequences of numeric and alphabetic characters, indicating a focus on numerical values and variables in mathematical contexts

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

    math notation with greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.79
    DIPSETTING
    -0.69
    دانشنامهٔ
    -0.68
    ValueStyle
    -0.61
     للمعارف
    -0.60
    aarrggbb
    -0.60
    hyrchwyd
    -0.60
    ContentAlignment
    -0.60
    DeleteBehavior
    -0.59
    ItemBackground
    -0.58
    POSITIVE LOGITS
    requestCode
    0.32
     Consultez
    0.31
     flamme
    0.30
     folhas
    0.29
    erweise
    0.28
     Longueur
    0.28
    wachsene
    0.27
     houſe
    0.27
     ſhe
    0.27
     betreft
    0.26
    Act Density 0.113%

    No Known Activations