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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wany
    1.02
    ur
    0.97
    ח
    0.97
    ോധ
    0.90
    un
    0.89
    handler
    0.88
    irre
    0.86
    hall
    0.85
    pets
    0.85
    child
    0.85
    POSITIVE LOGITS
     الاست
    0.90
     Inte
    0.86
    ก
    0.83
    ௭
    0.82
     است
    0.81
     ASCII
    0.80
    등
    0.79
    ูก
    0.78
     considère
    0.77
    ToProps
    0.76
    Act Density 0.000%

    No Known Activations