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

    Neuronpedia

    INDEX
    Explanations

    armor and uniforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    time
    0.65
     sorte
    0.62
    d
    0.61
    p
    0.61
    0.61
    "
    0.61
    o
    0.60
    珮
    0.60
    l
    0.58
    ton
    0.57
    POSITIVE LOGITS
     জার্সি
    0.68
     cladding
    0.64
    সজ্জিত
    0.62
     다만
    0.60
     gowns
    0.59
    ،
    0.59
     uniforms
    0.57
     clad
    0.56
     衣装
    0.56
     awarding
    0.55
    Act Density 0.013%

    No Known Activations