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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     మరియు
    0.70
    ির
    0.68
    spicuous
    0.67
     torpedo
    0.65
     желе
    0.63
     unreasonably
    0.63
    or
    0.61
    ﻳ
    0.61
    常量
    0.60
     futures
    0.59
    POSITIVE LOGITS
    Tela
    0.66
    الم
    0.65
    מות
    0.65
    .!
    0.65
    Species
    0.64
     انداز
    0.62
    మ్‌
    0.62
    ]]).
    0.62
    足り
    0.61
    נ
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.