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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oyeva
    1.22
    🤜
    1.20
    📛
    1.19
     diciendo
    1.12
     cumplir
    1.11
     cucumbers
    1.11
    嗬
    1.06
     ситуацию
    1.06
    ❣
    1.02
     cumplimiento
    1.02
    POSITIVE LOGITS
     Archiv
    0.86
    Bibli
    0.84
    bibli
    0.79
    folds
    0.77
    s
    0.75
    భా
    0.74
    <0x0D>
    0.73
    Philos
    0.72
    ไม่
    0.70
    8
    0.70
    Act Density 0.000%

    No Known Activations