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

    Neuronpedia

    INDEX
    Explanations

    statistics and representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teşekkür
    -0.07
     Yas
    -0.06
     PageSize
    -0.06
     teaching
    -0.06
    蒱
    -0.06
     аб
    -0.06
    _transient
    -0.06
     wnd
    -0.06
    ."_
    -0.06
     Ting
    -0.06
    POSITIVE LOGITS
     Bere
    0.07
    们
    0.07
     Builds
    0.07
    Scalar
    0.06
     hull
    0.06
     Yourself
    0.06
     blev
    0.06
    反而
    0.06
     Vill
    0.06
    砹
    0.06
    Act Density 0.030%

    No Known Activations