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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ,_-
    0.87
    yw
    0.80
    j
    0.77
    𝟕
    0.76
    icat
    0.75
     তুলতে
    0.71
     зака
    0.69
    eluarkan
    0.68
    Š
    0.68
    大多數
    0.68
    POSITIVE LOGITS
    т
    0.80
     earnest
    0.75
    serif
    0.74
    ρίου
    0.70
    後に
    0.68
    ственную
    0.67
    にか
    0.66
     Văn
    0.66
    についての
    0.66
    ственное
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.