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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dispose
    -0.08
    -football
    -0.07
     �
    -0.07
     dõi
    -0.07
    细致
    -0.07
    _Vector
    -0.07
    ยาย
    -0.07
    寥
    -0.07
     Fehler
    -0.06
     Eyl
    -0.06
    POSITIVE LOGITS
     yard
    0.07
    .NUM
    0.07
    UMMY
    0.07
     Hib
    0.06
     skew
    0.06
     certified
    0.06
    姑
    0.06
    לי
    0.06
    她们
    0.06
    闪
    0.06
    Act Density 0.002%

    No Known Activations