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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataContext
    -0.07
    Used
    -0.07
     находится
    -0.07
     יצא
    -0.07
    ducted
    -0.07
     порядке
    -0.07
     managers
    -0.06
    Manufacturer
    -0.06
    ятся
    -0.06
    大学毕业
    -0.06
    POSITIVE LOGITS
    舐
    0.07
     Zap
    0.07
    醑
    0.07
     Alg
    0.06
     Serg
    0.06
    _dep
    0.06
    걱
    0.06
    鲅
    0.06
    嵅
    0.06
     Kis
    0.06
    Act Density 0.082%

    No Known Activations