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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    seats
    0.87
    ua
    0.80
    inda
    0.79
    ire
    0.79
    jars
    0.77
    slides
    0.77
    ten
    0.76
    ions
    0.75
    rische
    0.74
    ுடைய
    0.73
    POSITIVE LOGITS
    Durante
    0.91
    På
    0.91
    ק
    0.91
    Después
    0.89
     flaming
    0.88
    Número
    0.87
    Dalam
    0.86
    לו
    0.84
    カル
    0.83
    CenterX
    0.83
    Act Density 0.002%

    No Known Activations