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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     księg
    -0.07
     Movies
    -0.07
     tempList
    -0.07
     Etsy
    -0.07
    帥
    -0.07
     PendingIntent
    -0.07
     arsch
    -0.07
    包子
    -0.07
    .dst
    -0.07
    子孙
    -0.07
    POSITIVE LOGITS
    垏
    0.07
     tooth
    0.07
    托
    0.07
     Ken
    0.06
     tus
    0.06
    感触
    0.06
     Minimum
    0.06
    請您
    0.06
    困难
    0.06
    :CGRect
    0.06
    Act Density 0.001%

    No Known Activations