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

    Neuronpedia

    INDEX
    Explanations

    word list structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questions
    0.70
    erté
    0.70
     ప్రశ్న
    0.68
     vowed
    0.67
    衤
    0.67
    ่น
    0.65
     vow
    0.65
     '[
    0.64
    questions
    0.63
    !',
    0.63
    POSITIVE LOGITS
    ستخدم
    0.75
    ន្ធ
    0.73
     Dazu
    0.71
    ের
    0.69
    ление
    0.67
    ség
    0.66
    sphere
    0.66
    兌
    0.66
    ncbi
    0.65
    ળ
    0.65
    Act Density 0.000%

    No Known Activations