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

    Neuronpedia

    INDEX
    Explanations

    most proper components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.80
    न
    0.77
    os
    0.71
    ン
    0.69
    ER
    0.65
    وپ
    0.64
    er
    0.64
    upport
    0.63
     звезд
    0.63
    ACH
    0.62
    POSITIVE LOGITS
    да
    0.73
    ב
    0.69
    els
    0.66
    alls
    0.65
    га
    0.64
    aje
    0.63
    汢
    0.61
     Caucus
    0.60
    icular
    0.59
    bs
    0.59
    Act Density 1.294%

    No Known Activations