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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    на
    2.08
    er
    1.89
    ️
    1.76
    ㅋ
    1.75
    ן
    1.63
    oretically
    1.59
    1.54
    눠
    1.52
    ه
    1.51
    ם
    1.51
    POSITIVE LOGITS
     sails
    1.86
     puluh
    1.84
     disposiciones
    1.82
     progressivement
    1.81
     পক্ষে
    1.80
    tion
    1.78
    cento
    1.73
    假日
    1.70
    សម្រាប់ការ
    1.69
    inez
    1.68
    Act Density 0.000%

    No Known Activations