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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ine
    0.70
    all
    0.66
    elernt
    0.66
    ANG
    0.65
    spec
    0.63
     Disposition
    0.63
    ina
    0.62
    ato
    0.61
    ris
    0.61
    Disposition
    0.61
    POSITIVE LOGITS
     adware
    0.93
    ৩
    0.92
    ৮
    0.91
     двох
    0.90
    м
    0.88
    २
    0.88
     такі
    0.87
    ⎛
    0.86
     Мі
    0.85
     Зу
    0.85
    Act Density 0.000%

    No Known Activations