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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    incre
    -0.08
    רש
    -0.07
    书香
    -0.07
     deber
    -0.07
    REDIS
    -0.07
     haus
    -0.07
     zob
    -0.07
    clr
    -0.07
     userInfo
    -0.07
     Trip
    -0.07
    POSITIVE LOGITS
    Cast
    0.07
    奥运会
    0.07
    ками
    0.07
     Lutheran
    0.07
     사랑
    0.06
     Rather
    0.06
     measurement
    0.06
     joined
    0.06
    eceğini
    0.06
     classic
    0.06
    Act Density 0.001%

    No Known Activations