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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonrası
    -0.07
     offenses
    -0.06
     setPassword
    -0.06
     AuthService
    -0.06
     основном
    -0.06
     ا�
    -0.06
     οργ
    -0.06
     �
    -0.06
    фт
    -0.06
    <long
    -0.06
    POSITIVE LOGITS
    (properties
    0.07
     《
    0.07
     Giám
    0.06
     ресур
    0.06
     Phòng
    0.06
    …"
    0.06
    ills
    0.06
    İY
    0.06
    änger
    0.06
    errals
    0.06
    Act Density 0.056%

    No Known Activations