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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Poinc
    0.42
     দৈর্ঘ
    0.42
     eerst
    0.40
     الخط
    0.40
     шабло
    0.39
     Encryption
    0.39
     مذہب
    0.39
     regression
    0.39
     exponential
    0.39
     Josephine
    0.39
    POSITIVE LOGITS
    ibur
    0.39
    ুদ
    0.38
    Gb
    0.36
    imit
    0.36
    avalt
    0.36
    abad
    0.36
    uillez
    0.35
    imt
    0.35
    YM
    0.35
    ல்க
    0.35
    Act Density 0.002%

    No Known Activations