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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     primitive
    0.80
     अथवा
    0.77
     vehicular
    0.74
     analog
    0.70
     rudimentary
    0.68
     unanticipated
    0.68
     alcun
    0.68
     puissant
    0.67
    かもしれませんが
    0.67
    乃至
    0.66
    POSITIVE LOGITS
     newsletters
    0.88
    ❤️
    0.84
     carers
    0.84
    佢
    0.80
     ragazze
    0.79
     reassure
    0.78
     பெண்கள்
    0.78
     rekla
    0.77
     żeby
    0.77
    毎年
    0.77
    Act Density 0.050%

    No Known Activations