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

    Neuronpedia

    INDEX
    Explanations

    data types and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cravings
    0.95
     wet
    0.85
     Jesu
    0.81
     Hoffmann
    0.80
     prostitutes
    0.79
    涸
    0.79
     Indianapolis
    0.78
     stationed
    0.77
    ijuana
    0.77
    ズム
    0.76
    POSITIVE LOGITS
    boolean
    1.63
    bool
    1.58
     boolean
    1.57
     bool
    1.53
    Boolean
    1.52
    Bool
    1.52
     Float
    1.45
    Float
    1.44
     Bool
    1.41
     tuple
    1.39
    Act Density 0.541%

    No Known Activations