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

    Neuronpedia

    INDEX
    Explanations

    left followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ek
    1.88
    fice
    1.88
    er
    1.76
     variés
    1.76
    ៉
    1.71
    ্স
    1.70
    Than
    1.70
    스를
    1.69
    ளில்
    1.68
    자
    1.66
    POSITIVE LOGITS
    s
    2.42
    ের
    2.14
     rept
    1.88
    სი
    1.81
     ventricle
    1.80
     humor
    1.77
     говорят
    1.77
     आपले
    1.77
    ों
    1.73
     coch
    1.73
    Act Density 0.001%

    No Known Activations