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

    Neuronpedia

    INDEX
    Explanations

    garments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěz
    -0.08
     威
    -0.08
     zwa
    -0.08
     incest
    -0.07
     divorced
    -0.07
    authorization
    -0.07
     justiça
    -0.07
     правительства
    -0.07
     bankruptcy
    -0.07
    ancestor
    -0.07
    POSITIVE LOGITS
     garments
    0.10
     garment
    0.09
     comfy
    0.09
     apparel
    0.08
    Variation
    0.08
     canvas
    0.08
     comfortably
    0.08
    Comfort
    0.08
    Variants
    0.08
    Positions
    0.08
    Act Density 0.006%

    No Known Activations