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

    Neuronpedia

    INDEX
    Explanations

    Technical terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    种子
    -0.08
    阏
    -0.08
    )'),
    -0.07
    _again
    -0.07
     emerging
    -0.07
    음을
    -0.07
    信息安全
    -0.07
    โต
    -0.07
     Records
    -0.07
    -direct
    -0.06
    POSITIVE LOGITS
    嫘
    0.07
    uspendLayout
    0.06
    偿还
    0.06
    _digest
    0.06
     Neighborhood
    0.06
    ḥ
    0.06
    lä
    0.06
    lord
    0.06
    岑
    0.06
    Peter
    0.06
    Act Density 0.635%

    No Known Activations