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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    free
    0.47
    natural
    0.42
     கான்
    0.41
     free
    0.41
     Arithmetic
    0.41
    ateg
    0.41
    ্যাটে
    0.40
     Free
    0.38
    ო
    0.38
     natural
    0.38
    POSITIVE LOGITS
    DOUT
    0.41
     Doyle
    0.41
     Isis
    0.41
     Doris
    0.41
    дко
    0.39
     adjourn
    0.38
     Daph
    0.38
    挥
    0.38
    尊
    0.38
     ifelse
    0.37
    Act Density 0.000%

    No Known Activations