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

    Neuronpedia

    INDEX
    Explanations

    18

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pay
    -0.07
     lin
    -0.06
    ्य
    -0.06
    年度
    -0.06
     kriz
    -0.06
     ys
    -0.06
     Widget
    -0.06
    Dates
    -0.06
     Himself
    -0.05
     Singap
    -0.05
    POSITIVE LOGITS
     инфек
    0.09
    .IsTrue
    0.07
    ンブ
    0.07
    駅徒歩
    0.07
     delight
    0.07
    _SIGNATURE
    0.07
     Budd
    0.06
     CharSet
    0.06
    .getTransaction
    0.06
    _FOR
    0.06
    Act Density 0.000%

    No Known Activations