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

    Neuronpedia

    INDEX
    Explanations

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Key
    -0.08
     هاتف
    -0.07
    مائة
    -0.07
    .connector
    -0.06
     spur
    -0.06
    Alive
    -0.06
    load
    -0.06
    强调
    -0.06
    �
    -0.06
    微信号
    -0.06
    POSITIVE LOGITS
     Hispan
    0.07
    쵝
    0.07
     Egypt
    0.07
    נטל
    0.07
    outdir
    0.07
    RAP
    0.07
    istrates
    0.07
    רום
    0.07
     사람들
    0.07
     Prediction
    0.06
    Act Density 0.007%

    No Known Activations