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

    Neuronpedia

    INDEX
    Explanations

    python type checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    double
    0.64
     Double
    0.63
     double
    0.63
    Double
    0.59
     DOUBLE
    0.59
    DOUBLE
    0.57
     doble
    0.52
     डबल
    0.49
     doppia
    0.48
     двой
    0.46
    POSITIVE LOGITS
     str
    1.04
    str
    0.93
    Str
    0.58
     int
    0.57
     strang
    0.53
     bool
    0.53
     Str
    0.52
     стр
    0.51
     STR
    0.51
     Strath
    0.49
    Act Density 0.020%

    No Known Activations