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

    Neuronpedia

    INDEX
    Explanations

    lists and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    1.97
    ség
    1.88
    它
    1.76
    }`;
    1.73
    s
    1.73
     età
    1.66
     naran
    1.65
     和
    1.63
     edizione
    1.62
    𝖓
    1.55
    POSITIVE LOGITS
    ان
    2.81
    на
    2.73
    an
    2.72
    ಾ
    2.67
    is
    2.45
    quele
    2.44
    quela
    2.42
    ल
    2.14
    ून
    2.02
    <blockquote>
    1.98
    Act Density 0.353%

    No Known Activations