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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     historians
    -0.07
    文化交流
    -0.07
    illin
    -0.07
    layın
    -0.07
    핥
    -0.07
    ab
    -0.07
    כב
    -0.07
    焕
    -0.07
    דיו
    -0.07
    кс
    -0.07
    POSITIVE LOGITS
    .Sn
    0.07
    見積
    0.07
     �
    0.06
     Nar
    0.06
     totals
    0.06
     Sept
    0.06
    _reset
    0.06
    Trip
    0.06
     squarely
    0.06
    本事
    0.06
    Act Density 0.003%

    No Known Activations