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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ای
    1.02
    ה
    0.93
    大
    0.92
    +\
    0.89
     הכ
    0.88
    z
    0.84
    of
    0.83
    ﺪ
    0.83
    م
    0.82
    由
    0.82
    POSITIVE LOGITS
    స్కీ
    1.07
     doorways
    0.96
     gaskets
    0.88
    ä
    0.88
     deportivos
    0.87
    ור
    0.85
     kojima
    0.85
     sauces
    0.84
     logiciels
    0.83
     detergents
    0.82
    Act Density 0.081%

    No Known Activations