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

    Neuronpedia

    INDEX
    Explanations

    what makes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ల
    0.73
     incluyendo
    0.69
    c
    0.69
    Reduce
    0.65
    ៨
    0.65
    Ꮲ
    0.65
     الرخصة
    0.64
    ס
    0.64
    ิ
    0.63
    姆
    0.63
    POSITIVE LOGITS
    (
    0.75
    ya
    0.70
    -
    0.65
    els
    0.64
    tes
    0.64
    esar
    0.61
    emptive
    0.60
    yan
    0.59
    äh
    0.58
    arant
    0.58
    Act Density 0.021%

    No Known Activations