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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...@
    -0.54
    bö
    -0.46
    <bos>
    -0.46
     record
    -0.44
     MECHAN
    -0.44
     PublicKey
    -0.44
    бя
    -0.44
    ürk
    -0.44
    ondi
    -0.44
    ):=\
    -0.44
    POSITIVE LOGITS
     kaynağından
    0.71
     مشارکت‌کنندگان
    0.71
     OFDb
    0.69
    tagHelperRunner
    0.67
    addContainerGap
    0.66
     متعلقه
    0.63
    存于互联网档案馆
    0.61
     Rajah
    0.60
     ProtoMessage
    0.59
     TDA
    0.59
    Act Density 0.015%

    No Known Activations