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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    LI
    0.93
    LA
    0.92
    RNA
    0.91
    RT
    0.89
    LO
    0.89
    LE
    0.87
    Lights
    0.82
    ult
    0.81
    LS
    0.80
    RE
    0.80
    POSITIVE LOGITS
    lerle
    0.77
     restricts
    0.73
    們
    0.73
     مربع
    0.72
     encased
    0.71
     तरीका
    0.71
     говорят
    0.70
     ensures
    0.69
    lerine
    0.69
    avers
    0.69
    Act Density 0.000%

    No Known Activations