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

    Neuronpedia

    INDEX
    Explanations

    .Assert

    np_max-act · gemini-2.0-flash

    Java unit-test code that uses static imports for assertions and related utility methods.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    _FALL
    -0.08
     đự
    -0.07
    蘖
    -0.07
     значительно
    -0.07
    �
    -0.07
    prefer
    -0.07
     tất
    -0.07
    相信大家
    -0.07
    犷
    -0.07
    rieving
    -0.07
    POSITIVE LOGITS
    知识分子
    0.07
     hart
    0.07
     $"
    0.07
    igung
    0.07
    ologue
    0.07
     thirty
    0.07
     формы
    0.07
    开口
    0.07
    \")
    0.06
    悪い
    0.06
    Act Density 0.000%

    No Known Activations