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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    libc
    0.39
    ütfen
    0.38
     все
    0.38
    brando
    0.38
    Все
    0.36
    限界
    0.36
    ctree
    0.36
     रिप्रोडक्शन
    0.35
    Bitte
    0.35
     Все
    0.35
    POSITIVE LOGITS
     his
    0.68
    his
    0.61
    他的
    0.53
    彼の
    0.53
     His
    0.52
     HIS
    0.49
     above
    0.49
     njegov
    0.49
    His
    0.47
     သူ့
    0.47
    Act Density 0.000%

    No Known Activations