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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ر
    0.52
    Video
    0.50
    ش
    0.49
    ان
    0.49
     Popul
    0.48
    盻
    0.48
    Laser
    0.47
    Sexy
    0.47
     Synchronization
    0.46
    Popul
    0.46
    POSITIVE LOGITS
     then
    0.57
     kind
    0.55
     thickness
    0.54
     tense
    0.54
     replace
    0.51
     carry
    0.50
     daya
    0.50
     damages
    0.50
     soles
    0.50
    ?
    0.50
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.