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

    Neuronpedia

    INDEX
    Explanations

    work with entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝓃
    0.73
    膦
    0.59
     arba
    0.56
    bursement
    0.55
     وصلت
    0.54
    م
    0.53
    Бі
    0.51
    讲话
    0.49
    집
    0.49
     انجن
    0.49
    POSITIVE LOGITS
    1
    0.82
    は
    0.73
    You
    0.67
    ing
    0.66
    (
    0.64
     with
    0.63
    ING
    0.62
    th
    0.59
    ’
    0.59
     on
    0.59
    Act Density 0.071%

    No Known Activations