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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (U
    -0.07
     Fut
    -0.07
    ük
    -0.07
     hmac
    -0.07
     (�
    -0.06
     fier
    -0.06
     ベ
    -0.06
     المؤ
    -0.06
    spacer
    -0.06
    enddate
    -0.06
    POSITIVE LOGITS
     logic
    0.06
     commercial
    0.06
     AppBar
    0.06
    .form
    0.06
     birth
    0.06
     ceilings
    0.06
    NJ
    0.06
     Blood
    0.06
     mounted
    0.06
     Address
    0.06
    Act Density 0.084%

    No Known Activations