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

    Neuronpedia

    INDEX
    Explanations

    few common methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ें
    0.84
    em
    0.76
    лас
    0.76
    OTHER
    0.73
    作成
    0.72
    כ
    0.72
    αι
    0.72
    ות
    0.71
    el
    0.71
    و
    0.71
    POSITIVE LOGITS
     rejuvenating
    1.13
    showroom
    1.07
     maart
    1.04
     hochwert
    1.03
    trend
    1.02
     pessoas
    1.01
     meningkatkan
    1.01
    ชาว
    1.01
    驥
    1.00
     rejuvenate
    1.00
    Act Density 0.000%

    No Known Activations