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
     indictment
    -0.07
    (fileName
    -0.06
    da
    -0.06
     used
    -0.06
     Assad
    -0.06
     log
    -0.06
    kanı
    -0.06
     precis
    -0.06
     load
    -0.06
     Seat
    -0.06
    POSITIVE LOGITS
    ーチ
    0.07
    信息
    0.07
     aliqu
    0.07
     nonzero
    0.07
    ाकर
    0.07
     Ali
    0.07
    �
    0.07
    情報
    0.07
    [key
    0.07
     meget
    0.07
    Act Density 0.003%

    No Known Activations