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

    Neuronpedia

    INDEX
    Explanations

    voltage regulator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.67
    a
    0.59
    g
    0.53
    b
    0.51
    nde
    0.51
    ae
    0.49
    anima
    0.48
    ag
    0.47
    M
    0.46
    t
    0.46
    POSITIVE LOGITS
    キ
    0.54
     фестива
    0.52
     設定
    0.52
     війни
    0.52
    ких
    0.49
     بتكون
    0.49
    গুণ
    0.47
     工程
    0.46
    朼
    0.46
    発展
    0.46
    Act Density 0.000%

    No Known Activations