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

    Neuronpedia

    INDEX
    Explanations

    Dreaming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    e
    -0.88
    i
    -0.88
    s
    -0.73
    a
    -0.72
    ed
    -0.68
    es
    -0.60
    ی
    -0.60
     quæ
    -0.59
    ik
    -0.58
    say
    -0.58
    POSITIVE LOGITS
    extAlignment
    0.81
     Мексичка
    0.79
    GEBURTSDATUM
    0.70
     HasFactory
    0.68
     للمعارف
    0.67
    GEBURTS
    0.66
    clerview
    0.63
    tershire
    0.63
    figsize
    0.63
    knecht
    0.63
    Act Density 0.300%

    No Known Activations