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

    Neuronpedia

    INDEX
    Explanations

    identifying top percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    バー
    0.54
    ポ
    0.52
     erased
    0.50
    يح
    0.50
     slogans
    0.49
    、
    0.49
    （
    0.48
    ・
    0.47
     invariably
    0.47
     exudes
    0.46
    POSITIVE LOGITS
    cích
    0.62
     நாளில்
    0.59
     постро
    0.57
    crit
    0.54
    अलग
    0.54
    các
    0.53
    a
    0.53
     tăng
    0.51
     до
    0.50
    c
    0.50
    Act Density 0.000%

    No Known Activations