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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     that
    0.39
     be
    0.34
    0.34
    พ
    0.31
     from
    0.30
    i
    0.30
     at
    0.30
    σ
    0.30
     retribution
    0.29
    ร
    0.29
    POSITIVE LOGITS
     అందించ
    0.28
    анг
    0.27
    മെ
    0.27
    IdleSync
    0.26
    cevam
    0.26
    álló
    0.26
     Пол
    0.26
    åll
    0.26
     தேர்ந்தெடுக்க
    0.26
    𝑫
    0.26
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.