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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iguity
    0.79
    market
    0.75
    bound
    0.75
    istir
    0.75
    affiliated
    0.74
    manage
    0.72
    set
    0.71
    /)
    0.71
     WARNING
    0.71
    PHONE
    0.71
    POSITIVE LOGITS
     scars
    0.82
    я
    0.80
    नी
    0.79
     Galaxies
    0.77
    ੌਰ
    0.75
     dimensioni
    0.74
     samo
    0.72
    りたい
    0.72
    絭
    0.71
     lateribus
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.