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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.86
     sprouts
    0.77
     Ro
    0.73
     tk
    0.73
     say
    0.70
     Luke
    0.70
     dances
    0.70
     affliction
    0.70
     fumes
    0.70
     Puppy
    0.70
    POSITIVE LOGITS
    𝙨
    1.03
    ņu
    0.97
    daten
    0.95
    𝙙
    0.95
    𝗡
    0.93
    THING
    0.92
    dimensioni
    0.91
    њ
    0.91
    𝙎
    0.89
    𝗴
    0.89
    Act Density 0.000%

    No Known Activations