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

    Neuronpedia

    INDEX
    Explanations

    under body part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.91
    स
    0.79
    ס
    0.77
    ל
    0.76
    с
    0.75
    '.
    0.75
    '।
    0.72
    иск
    0.71
    ल
    0.68
    ல்
    0.68
    POSITIVE LOGITS
    0.72
    页
    0.69
    進
    0.65
    ధ్య
    0.60
    ंसारी
    0.59
    酒
    0.59
     ETF
    0.59
    of
    0.58
    阶段
    0.58
    茶
    0.58
    Act Density 0.001%

    No Known Activations