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

    Neuronpedia

    INDEX
    Explanations

    my

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Bytes
    -0.07
    الة
    -0.07
    شب
    -0.07
     Keeper
    -0.07
    명
    -0.06
    .mean
    -0.06
    (Time
    -0.06
    (pe
    -0.06
    ("?
    -0.06
    _que
    -0.06
    POSITIVE LOGITS
    ActionTypes
    0.07
     original
    0.06
     mid
    0.06
    Intern
    0.06
    HomeAsUp
    0.06
     Intern
    0.06
     nightlife
    0.06
    rootScope
    0.06
     امنیت
    0.06
     nuestras
    0.06
    Act Density 0.067%

    No Known Activations