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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.19
    ों
    1.05
    ς
    0.94
    ۲
    0.85
    ۹
    0.84
    sons
    0.79
    ١
    0.79
    ój
    0.78
    ség
    0.78
    ٧
    0.78
    POSITIVE LOGITS
     следует
    0.89
     patitth
    0.88
    йдз
    0.82
    лады
    0.80
     тихо
    0.79
     ettha
    0.79
     выглядит
    0.79
     exudes
    0.77
     havoc
    0.77
     kammam
    0.76
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.