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

    Neuronpedia

    INDEX
    Explanations

    int type in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brighton
    0.84
     prompt
    0.73
     continued
    0.73
     ABC
    0.73
     Rachel
    0.73
     XD
    0.73
     rein
    0.72
     Epsom
    0.71
     allergies
    0.71
     erasure
    0.70
    POSITIVE LOGITS
    int
    1.42
     int
    1.23
    struct
    1.12
    void
    0.97
    typedef
    0.92
    INT
    0.91
     struct
    0.89
    祅
    0.87
    Int
    0.83
    unsigned
    0.80
    Act Density 0.037%

    No Known Activations