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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ם
    2.12
    thought
    1.82
    mers
    1.79
    ں
    1.79
    िल
    1.75
    Limitations
    1.72
    S
    1.72
    survival
    1.71
    ं
    1.69
    t
    1.68
    POSITIVE LOGITS
     LikeLike
    2.31
    ు
    2.26
    я
    2.11
     saudável
    2.06
    ை
    2.01
     nums
    2.00
    ressions
    1.95
     oui
    1.94
     winnings
    1.93
     procedente
    1.89
    Act Density 0.000%

    No Known Activations