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

    Neuronpedia

    INDEX
    Explanations

    positive/negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NEO
    -0.07
    PARAM
    -0.06
     tokenizer
    -0.06
     مرتب
    -0.06
     Moral
    -0.06
    監
    -0.06
    IED
    -0.06
    Area
    -0.06
     Cor
    -0.06
     Ip
    -0.06
    POSITIVE LOGITS
    ısını
    0.07
    是一个
    0.06
    ってる
    0.06
     آنلاین
    0.06
    mentioned
    0.06
    ��
    0.06
     gou
    0.06
    _bases
    0.06
     Campus
    0.06
     Gst
    0.06
    Act Density 0.138%

    No Known Activations