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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    seekers
    0.43
     offenders
    0.42
     шә
    0.40
     seekers
    0.40
     dampened
    0.40
    ಾಪ
    0.38
    hunters
    0.38
     myth
    0.38
    mapped
    0.37
    ientos
    0.36
    POSITIVE LOGITS
    銳
    0.52
     Nakh
    0.44
    箋
    0.41
    Verlag
    0.40
    急性
    0.40
    锐
    0.40
     легко
    0.39
    責任
    0.39
    Bingo
    0.39
    ::<
    0.39
    Act Density 0.001%

    No Known Activations