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

    Neuronpedia

    INDEX
    Explanations

    df

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    万名
    -0.08
    However
    -0.07
     fourn
    -0.07
    خذ
    -0.07
    -0.07
    -0.07
    adden
    -0.07
    린
    -0.07
    \Storage
    -0.07
    wró
    -0.07
    POSITIVE LOGITS
     coat
    0.07
     outros
    0.06
     Tea
    0.06
    彬
    0.06
     carriage
    0.06
    (Set
    0.06
    (click
    0.06
    roperties
    0.06
     siege
    0.06
    =function
    0.06
    Act Density 0.011%

    No Known Activations