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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.12
    0
    0.85
    <0x80>
    0.83
     that
    0.82
    <
    0.77
    ’:
    0.77
    ’;
    0.75
    ’?
    0.72
    ’).
    0.71
    ’),
    0.71
    POSITIVE LOGITS
    ка
    0.80
    на
    0.71
    و
    0.69
    ك
    0.69
    скольку
    0.68
    도
    0.66
    ре
    0.66
    Tôi
    0.64
    Aqui
    0.63
     तरुणा
    0.63
    Act Density 0.480%

    No Known Activations