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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drs
    -0.07
     audi
    -0.06
     valore
    -0.06
    $c
    -0.06
     فشار
    -0.06
     onChanged
    -0.06
     sponge
    -0.06
    show
    -0.06
     decoder
    -0.06
    وزيع
    -0.06
    POSITIVE LOGITS
     Dominican
    0.07
     separates
    0.06
    <|eot_id|>
    0.06
     Hamburg
    0.06
    Strike
    0.06
    when
    0.06
     YA
    0.06
     Scatter
    0.06
    َّ
    0.06
     stores
    0.06
    Act Density 0.019%

    No Known Activations