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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    $\$
    0.39
    ipar
    0.38
    രിച്ചി
    0.37
    ంబేద్కర్
    0.37
     parole
    0.37
    פרי
    0.37
    osc
    0.36
     কহ
    0.36
     cubic
    0.36
    giz
    0.36
    POSITIVE LOGITS
     ಖ
    0.41
    চ্য
    0.41
     Effort
    0.40
    굵
    0.39
    㽞
    0.39
     pasti
    0.38
     給
    0.38
     আবাস
    0.38
     pumped
    0.38
     niets
    0.37
    Act Density 0.003%

    No Known Activations