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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes and possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    0.79
     are
    0.79
    ons
    0.73
    с
    0.72
    are
    0.72
     Фа
    0.71
    s
    0.66
    atthena
    0.66
    codiles
    0.66
    calories
    0.66
    POSITIVE LOGITS
    ו
    1.11
    ↵
    0.96
    在
    0.96
    ה
    0.85
    ב
    0.82
    ע
    0.82
     conceivably
    0.81
    <0x0D>
    0.79
     in
    0.79
    }
    0.79
    Act Density 0.350%

    No Known Activations