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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    andı
    0.96
    cted
    0.95
    რივი
    0.93
    క్
    0.87
    ahlt
    0.85
    ırım
    0.85
    ım
    0.83
     sufrimiento
    0.83
    lgende
    0.82
    ྔ
    0.82
    POSITIVE LOGITS
     ε
    0.82
    ulation
    0.75
     bot
    0.74
     ем
    0.73
     VIA
    0.72
     motor
    0.71
     poetry
    0.70
     slim
    0.70
     रस
    0.70
    Motor
    0.69
    Act Density 0.000%

    No Known Activations