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

    Neuronpedia

    INDEX
    Explanations

    arabic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strains
    -0.08
     Erkennt
    -0.08
     Gesamt
    -0.08
     Ausgabe
    -0.08
     Kost
    -0.08
     पठ
    -0.07
    [Serialize
    -0.07
     Kod
    -0.07
     Praxis
    -0.07
    pekte
    -0.07
    POSITIVE LOGITS
    هم
    0.08
    اً
    0.08
     الع
    0.08
    ٌ
    0.08
    كم
    0.08
    ها
    0.08
     ਸੀ
    0.08
    نا
    0.08
     الحكم
    0.08
     هو
    0.07
    Act Density 0.143%

    No Known Activations