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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     außergewöhn
    0.90
     apesar
    0.87
     несмотря
    0.84
     exuber
    0.83
     todas
    0.81
     todos
    0.81
     defies
    0.80
     kaleidoscope
    0.80
     plethora
    0.79
     afectar
    0.77
    POSITIVE LOGITS
    lr
    0.79
    y
    0.77
    p
    0.76
    n
    0.73
    i
    0.73
    o
    0.71
    k
    0.71
    t
    0.70
    nm
    0.70
    d
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.