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

    Neuronpedia

    INDEX
    Explanations

    hair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     styling
    0.54
    谢
    0.48
     Länge
    0.48
     styled
    0.47
     braid
    0.46
    dye
    0.46
     boucle
    0.44
     Styling
    0.44
     muss
    0.44
     braided
    0.44
    POSITIVE LOGITS
     hair
    2.31
     Hair
    2.19
    Hair
    2.17
    hair
    2.11
     HAIR
    1.95
     hairs
    1.67
     hår
    1.61
     haired
    1.56
     cabelo
    1.55
    ヘア
    1.54
    Act Density 0.024%

    No Known Activations