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

    Neuronpedia

    INDEX
    Explanations

    head covering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consented
    0.44
     paging
    0.44
    henol
    0.39
    coding
    0.39
    literal
    0.38
     फेस्टिव
    0.38
     sponsored
    0.38
    Delegate
    0.37
     दिवाली
    0.36
    箸
    0.35
    POSITIVE LOGITS
     cap
    0.71
    キャップ
    0.69
     Caps
    0.62
     Cap
    0.61
    Cap
    0.60
     कैप
    0.57
     caps
    0.56
     hairline
    0.54
     Capp
    0.53
     ক্যাপ
    0.53
    Act Density 0.015%

    No Known Activations