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

    Neuronpedia

    INDEX
    Explanations

    Cassandra

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ды
    -0.07
     Pay
    -0.07
     tempted
    -0.07
    ыт
    -0.06
    Encode
    -0.06
     Iterate
    -0.06
     ministries
    -0.06
    Sat
    -0.06
    _schema
    -0.06
    filepath
    -0.06
    POSITIVE LOGITS
     Indianapolis
    0.07
     Malaysian
    0.07
     εκ
    0.06
    .:.:.:
    0.06
     名無しさん
    0.06
    _kelas
    0.06
    -wsj
    0.06
     ECC
    0.06
    [MAX
    0.06
    قق
    0.06
    Act Density 0.002%

    No Known Activations