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

    Neuronpedia

    INDEX
    Explanations

    groups and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棋牌
    -0.08
    .Retrofit
    -0.07
     Gun
    -0.07
    ᆮ
    -0.07
     odom
    -0.07
    zeug
    -0.07
     deflate
    -0.07
    里面的
    -0.07
    igu
    -0.07
    oline
    -0.07
    POSITIVE LOGITS
     Batch
    0.07
    合作伙伴
    0.07
    _layer
    0.07
    Ｅ
    0.07
    ｰ
    0.07
     proceso
    0.07
     maxLength
    0.07
     helps
    0.06
    ߠ
    0.06
     thumbnail
    0.06
    Act Density 0.053%

    No Known Activations