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

    Neuronpedia

    INDEX
    Explanations

    blind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blind
    -1.33
    blind
    -1.19
     Blind
    -1.15
    Blind
    -1.07
     blindness
    -1.05
     blinded
    -1.03
     HasFactory
    -0.87
    blin
    -0.85
     noDo
    -0.79
     aveug
    -0.77
    POSITIVE LOGITS
    遣
    0.47
     of
    0.46
    ides
    0.45
    win
    0.43
     terk
    0.43
    well
    0.42
    Win
    0.42
    __).
    0.41
    četně
    0.41
     inté
    0.39
    Act Density 1.744%

    No Known Activations