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

    Neuronpedia

    INDEX
    Explanations

    public static void

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    私
    0.55
     privata
    0.45
     приват
    0.44
     தனியார்
    0.44
     प्राइवेट
    0.43
     PRIVATE
    0.43
     Private
    0.43
    Private
    0.41
     prywat
    0.41
    Wheat
    0.39
    POSITIVE LOGITS
     void
    2.70
    void
    2.44
     voids
    1.87
     Void
    1.65
    Void
    1.56
    VOID
    1.27
    Voids
    1.22
     voi
    1.05
     vo
    0.95
    voi
    0.90
    Act Density 0.022%

    No Known Activations