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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    重视
    -0.07
    宏观
    -0.07
    /sc
    -0.07
    完善
    -0.07
     cụ
    -0.07
    失误
    -0.07
     vide
    -0.07
     replacing
    -0.07
    载
    -0.06
    师
    -0.06
    POSITIVE LOGITS
     Erdoğan
    0.09
    _PROGRAM
    0.08
    _An
    0.07
     Trafford
    0.07
    .ElementAt
    0.07
     IonicPage
    0.07
    Prediction
    0.07
    _friend
    0.07
    _ALARM
    0.07
    eterangan
    0.07
    Act Density 0.008%

    No Known Activations