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

    Neuronpedia

    INDEX
    Explanations

    scientific structural analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BEL
    -0.07
    怔
    -0.07
     MAS
    -0.06
    弯曲
    -0.06
    疵
    -0.06
    奥巴
    -0.06
    茭
    -0.06
    oodles
    -0.06
    abal
    -0.06
    _FILL
    -0.06
    POSITIVE LOGITS
    __));↵
    0.07
    严格
    0.07
     runtime
    0.07
    ように
    0.07
     серии
    0.07
    一份
    0.07
    راجع
    0.07
     LOWER
    0.07
    _INITIALIZER
    0.06
     rang
    0.06
    Act Density 0.005%

    No Known Activations