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

    Neuronpedia

    INDEX
    Explanations

    features and components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wear
    1.15
     Wear
    0.97
    Wear
    0.97
    Skin
    0.90
    cotton
    0.83
     SKIN
    0.83
    frag
    0.81
     wear
    0.81
     ผ้า
    0.78
     Skin
    0.78
    POSITIVE LOGITS
    রাজের
    0.75
    か
    0.74
     か
    0.72
    রাজ
    0.70
    дера
    0.67
    ρια
    0.65
    يل
    0.65
     aperture
    0.65
    重
    0.65
     trimethyl
    0.64
    Act Density 0.000%

    No Known Activations