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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _browser
    -0.07
    其实
    -0.07
    /jpeg
    -0.07
     밤
    -0.06
    rawler
    -0.06
    �
    -0.06
     Yours
    -0.06
     Capitol
    -0.06
    аки
    -0.06
    вич
    -0.06
    POSITIVE LOGITS
    _signal
    0.07
     met
    0.07
    modelName
    0.06
    内容
    0.06
     بتوان
    0.06
    �
    0.06
    _CUDA
    0.06
    .one
    0.06
     blocking
    0.06
    кое
    0.06
    Act Density 0.033%

    No Known Activations