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

    Neuronpedia

    INDEX
    Explanations

    sociodemographic statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    上课
    -0.08
    命
    -0.08
    .Types
    -0.07
    raction
    -0.07
     duration
    -0.07
    镍
    -0.07
     Ge
    -0.06
    刚好
    -0.06
    .exchange
    -0.06
    恩
    -0.06
    POSITIVE LOGITS
    まず
    0.07
    凇
    0.07
     Ramos
    0.07
    .sal
    0.07
    环节
    0.06
     דול
    0.06
    桊
    0.06
    ละ
    0.06
    .slim
    0.06
    おい
    0.06
    Act Density 0.030%

    No Known Activations