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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پیام
    -0.07
    (gs
    -0.07
    Ut
    -0.06
    İ
    -0.06
     ương
    -0.06
    PasswordEncoder
    -0.06
     tai
    -0.06
    editor
    -0.06
    .Usuario
    -0.06
    uchar
    -0.06
    POSITIVE LOGITS
     дум
    0.06
     authenticated
    0.06
    "s
    0.06
     PL
    0.06
    лишком
    0.06
     Merkel
    0.06
    Dispatcher
    0.06
    พร
    0.06
    WillAppear
    0.06
    rawtypes
    0.06
    Act Density 0.009%

    No Known Activations