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

    Neuronpedia

    INDEX
    Explanations

    facial expressions and body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilisent
    0.49
     users
    0.47
     기반
    0.47
     venues
    0.46
     मूलभूत
    0.46
     companies
    0.46
     organisations
    0.46
     ourselves
    0.46
     yourselves
    0.46
     workflows
    0.46
    POSITIVE LOGITS
     drooping
    0.66
     furrow
    0.63
     wist
    0.61
     trembling
    0.60
     blushing
    0.59
     smile
    0.59
     blush
    0.59
     smiling
    0.57
     frown
    0.57
     blushed
    0.56
    Act Density 0.180%

    No Known Activations