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

    Neuronpedia

    INDEX
    Explanations

    varied Wikipedia articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.48
     masculine
    -0.45
     chivalry
    -0.41
    нциклопедия
    -0.40
    έα
    -0.39
     Salta
    -0.39
     boomer
    -0.39
     engraver
    -0.39
     Filt
    -0.39
     Josephus
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.87
     وتسجيلات
    0.72
     noDo
    0.72
     skolan
    0.70
    følgelig
    0.68
     nahilalakip
    0.68
     HasFactory
    0.68
    ">//
    0.67
     varandra
    0.66
    SequentialGroup
    0.65
    Act Density 0.087%

    No Known Activations