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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Frage
    0.53
    siblings
    0.50
     ప్రశ్న
    0.48
    ကျွန်
    0.48
    okhlov
    0.47
     প্রশ্নের
    0.47
     Collaborate
    0.46
    烪
    0.45
    প্রশ্ন
    0.45
    неоп
    0.45
    POSITIVE LOGITS
     replaced
    0.55
     introduced
    0.52
    lık
    0.52
     acted
    0.50
     centrifuged
    0.47
     detectable
    0.46
     overtaken
    0.44
     uređ
    0.44
     instead
    0.43
     rolled
    0.43
    Act Density 0.012%

    No Known Activations