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

    Neuronpedia

    INDEX
    Explanations

    mathematical and scientific formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上涨
    0.35
    高兴
    0.29
     использования
    0.29
    节省
    0.29
     శాతం
    0.28
    萜
    0.28
    脸上
    0.28
    语气
    0.28
    素质
    0.28
     сложности
    0.28
    POSITIVE LOGITS
    G
    0.43
    D
    0.41
    N
    0.41
    R
    0.41
    V
    0.41
    P
    0.40
    L
    0.40
    W
    0.40
    B
    0.39
    U
    0.38
    Act Density 0.153%

    No Known Activations