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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and landmarks

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

    regions and specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نص
    -0.31
    离
    -0.28
     delegación
    -0.28
    Presentation
    -0.28
    ساس
    -0.27
    ofType
    -0.27
    şiv
    -0.26
     kategori
    -0.26
     nahilalakip
    -0.26
    getCause
    -0.26
    POSITIVE LOGITS
     ModelExpression
    0.83
    хьтан
    0.71
    ########.
    0.71
    ंदीखरीदारी
    0.70
    CppMethod
    0.68
     NSCoder
    0.66
     ब्रेकडाउन
    0.63
    ReusableCell
    0.63
     AttributeSet
    0.63
    лтамалар
    0.63
    Act Density 0.141%

    No Known Activations