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

    Neuronpedia

    INDEX
    Explanations

    skin, hair, and beauty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Epilepsy
    0.76
     Adapter
    0.75
    面白い
    0.74
     Encoding
    0.73
    Adapter
    0.73
     adaptor
    0.72
    adapters
    0.72
     epile
    0.70
    reiber
    0.69
    clerosis
    0.69
    POSITIVE LOGITS
     glowing
    1.48
     radiant
    1.48
     healthy
    1.45
     radiance
    1.45
     glow
    1.42
     rejuvenated
    1.41
     refreshed
    1.35
     healthier
    1.32
     fresher
    1.31
     freshness
    1.24
    Act Density 0.138%

    No Known Activations