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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مجل
    -0.07
    घ
    -0.07
    昒
    -0.07
     quel
    -0.07
    ҥ
    -0.07
     consid
    -0.06
     alleging
    -0.06
     tầ
    -0.06
    غال
    -0.06
    ﯓ
    -0.06
    POSITIVE LOGITS
    ITS
    0.09
     BH
    0.07
    チャー
    0.07
    _forward
    0.07
     Hiện
    0.07
    襞
    0.07
     بطريقة
    0.07
    Born
    0.07
    .Deserialize
    0.07
     Implemented
    0.07
    Act Density 0.071%

    No Known Activations