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

    Neuronpedia

    INDEX
    Explanations

    protected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GP
    -0.07
     віз
    -0.07
     Daniels
    -0.06
     nut
    -0.06
    758
    -0.06
     khô
    -0.06
    kop
    -0.06
    NEL
    -0.06
     vět
    -0.06
    ヘ
    -0.06
    POSITIVE LOGITS
    .Unmarshal
    0.07
    formedURLException
    0.07
    尘
    0.07
    取得
    0.06
    Packet
    0.06
     evenings
    0.06
     原
    0.06
     sustained
    0.06
     установ
    0.06
     irc
    0.06
    Act Density 0.008%

    No Known Activations