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

    Neuronpedia

    INDEX
    Explanations

    t-shirt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ancias
    0.85
    絠
    0.75
     concor
    0.71
    ående
    0.70
    いや
    0.68
    imamente
    0.67
     মস্তিষ্
    0.66
    ificio
    0.65
     investigação
    0.64
    炀
    0.64
    POSITIVE LOGITS
     Shirt
    1.12
     T
    1.08
     shirt
    1.04
    Shirt
    1.03
     shirts
    0.97
    shirt
    0.97
    T
    0.97
     Shirts
    0.94
    Shirts
    0.85
     t
    0.84
    Act Density 0.085%

    No Known Activations