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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    丷
    0.76
     Normally
    0.72
     Incidentally
    0.70
    DOUBLE
    0.67
    normally
    0.66
    Normally
    0.65
    Closeup
    0.64
    Incidentally
    0.64
     Then
    0.63
     Foreground
    0.63
    POSITIVE LOGITS
     oils
    0.79
     Oils
    0.77
    مان
    0.77
    stes
    0.74
    防治
    0.73
    ل
    0.73
     sulfates
    0.72
     あん
    0.71
    liness
    0.70
    不需要
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.