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

    Neuronpedia

    INDEX
    Explanations

    small + appliances, pigs, businesses, cap, architectural

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    1.51
    de
    1.45
    がある
    1.30
    ડિયા
    1.25
    ᆼ
    1.24
    ел
    1.23
    Já
    1.23
    र्थ
    1.23
    𝖆
    1.23
    lah
    1.20
    POSITIVE LOGITS
    ก
    1.48
    емых
    1.48
    }$
    1.45
    ிக்க
    1.39
    ோ
    1.39
    pox
    1.38
    uwen
    1.36
    THING
    1.35
    того
    1.32
    ны
    1.31
    Act Density 0.072%

    No Known Activations