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

    Neuronpedia

    INDEX
    Explanations

    potential offense warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .filename
    -0.07
     charset
    -0.06
             
↵
    -0.06
     Produk
    -0.06
     bodies
    -0.06
     RUN
    -0.06
     authentic
    -0.06
     хорошо
    -0.06
     HUGE
    -0.06
     racist
    -0.06
    POSITIVE LOGITS
     vd
    0.06
    singleton
    0.06
    param
    0.06
    ertino
    0.06
    alace
    0.06
    ализа
    0.06
     Redskins
    0.06
    Aff
    0.06
    <TKey
    0.06
    _ini
    0.06
    Act Density 0.027%

    No Known Activations