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

    Neuronpedia

    INDEX
    Explanations

    GTA V

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.02
    ן
    1.02
     ذر
    0.84
    ."
    0.82
    ية
    0.80
    .\
    0.80
    myButtons
    0.80
    frequencies
    0.78
    resses
    0.77
    ن
    0.77
    POSITIVE LOGITS
     riesce
    1.02
    PTION
    1.02
    дят
    0.96
    ÓN
    0.95
     questione
    0.91
     directa
    0.90
     conséqu
    0.90
     aiutare
    0.90
     inclusiv
    0.89
    ımı
    0.89
    Act Density 0.002%

    No Known Activations