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

    Neuronpedia

    INDEX
    Explanations

    prohibition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gobierno
    -0.07
     Richards
    -0.07
     pitchers
    -0.07
     kadar
    -0.07
     öğrenc
    -0.07
    Stats
    -0.06
    κρα
    -0.06
     airports
    -0.06
     sw
    -0.06
    補
    -0.06
    POSITIVE LOGITS
     rot
    0.06
     muc
    0.06
     phil
    0.06
     introducing
    0.06
    unexpected
    0.06
    』（
    0.06
    oài
    0.06
     �
    0.06
    Recognizer
    0.05
     روشن
    0.05
    Act Density 0.027%

    No Known Activations