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

    Neuronpedia

    INDEX
    Explanations

    contrasting specialized vs. general

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺭ
    0.49
    timeLeft
    0.46
    '
    0.46
     tessel
    0.45
     capillary
    0.44
    `,
    0.43
    network
    0.43
    на
    0.43
    ަމ
    0.43
    タイル
    0.43
    POSITIVE LOGITS
    h
    0.50
    壮
    0.48
    k
    0.46
    不断
    0.46
    कु
    0.45
    undu
    0.42
     NHT
    0.42
    培养
    0.41
     vv
    0.41
    聸
    0.41
    Act Density 0.001%

    No Known Activations