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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kadın
    -0.07
    Median
    -0.07
    .dead
    -0.07
     Answer
    -0.07
    .table
    -0.06
     attributed
    -0.06
    CTOR
    -0.06
     Mandal
    -0.06
     PyTuple
    -0.06
    _CUR
    -0.06
    POSITIVE LOGITS
     ports
    0.07
     отв
    0.07
    보내기
    0.06
    shell
    0.06
    oice
    0.06
    isses
    0.06
     Trustees
    0.06
     فصل
    0.06
     nghiệm
    0.06
     機
    0.06
    Act Density 0.055%

    No Known Activations