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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    لي
    0.62
    zones
    0.51
    ವ
    0.50
    ﺩ
    0.49
    widgets
    0.46
    ethanol
    0.46
    DRO
    0.46
     షో
    0.45
    ي
    0.44
    ဧ
    0.44
    POSITIVE LOGITS
    พวก
    0.48
     unwillingness
    0.46
     prompted
    0.46
     समय
    0.45
    เวลา
    0.44
     bewust
    0.44
     notorious
    0.44
    ørt
    0.44
     signboard
    0.44
    ปฏิบัติ
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.