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

    Neuronpedia

    INDEX
    Explanations

    Index files and directories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adopt
    -0.06
     chair
    -0.06
     škol
    -0.06
     ذكر
    -0.06
     أحد
    -0.06
     Caught
    -0.06
    _backup
    -0.06
    [temp
    -0.06
     Haw
    -0.06
    程序
    -0.06
    POSITIVE LOGITS
    (statearr
    0.07
    ConverterFactory
    0.07
     dil
    0.06
     \"
    0.06
    	th
    0.06
    -outline
    0.06
    .DialogResult
    0.06
    @stop
    0.06
     reviewer
    0.06
     kurtul
    0.06
    Act Density 0.009%

    No Known Activations