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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     burnout
    0.80
     chat
    0.79
     overheat
    0.78
     antihist
    0.76
    yzed
    0.75
     beet
    0.74
     atualmente
    0.74
     rectMode
    0.74
     étudi
    0.73
     wakt
    0.73
    POSITIVE LOGITS
    raising
    0.74
    ñ
    0.72
    r
    0.68
    下午
    0.68
    ṣ
    0.66
     Ghosh
    0.66
     রশিদ
    0.65
    W
    0.65
    niv
    0.64
    é
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.