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

    Neuronpedia

    INDEX
    Explanations

    list separators and parenthetical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.43
    ae
    0.41
    大家
    0.41
    itet
    0.39
    ap
    0.39
    几次
    0.39
    ho
    0.38
    orderBy
    0.38
    口袋
    0.38
    ia
    0.38
    POSITIVE LOGITS
    នូវ
    0.49
     vorm
    0.47
     худож
    0.46
    린다
    0.45
     Lenz
    0.44
    ഓ
    0.44
     відбу
    0.44
    Бе
    0.43
    🄴
    0.43
     sınıf
    0.42
    Act Density 0.001%

    No Known Activations