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

    Neuronpedia

    INDEX
    Explanations

    text to columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Castle
    0.46
    enaar
    0.46
     опять
    0.42
    ีย์
    0.42
    Meer
    0.42
     アイアン
    0.42
    Cast
    0.41
     artistas
    0.41
    uminescence
    0.41
    Sab
    0.41
    POSITIVE LOGITS
     도입
    0.44
    ಂಗ್ರೆ
    0.44
    ۴
    0.42
    μον
    0.42
     ವೇಳ
    0.41
    4
    0.41
     그러나
    0.41
    😣
    0.40
    TypeId
    0.40
    bypass
    0.40
    Act Density 0.005%

    No Known Activations