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

    Neuronpedia

    INDEX
    Explanations

    absolute insult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veoma
    0.63
     ক্ষমতা
    0.62
    jskim
    0.62
     طريقة
    0.60
    ᱲ
    0.57
    ικής
    0.55
     Gemeins
    0.54
    ামূলক
    0.54
    ικές
    0.54
     surjective
    0.54
    POSITIVE LOGITS
     mess
    1.33
     caricature
    1.29
     monstros
    1.18
     messes
    1.17
     monolith
    1.11
     monsters
    1.11
     wreck
    1.08
     disaster
    1.07
     embodiment
    1.06
     hulk
    1.05
    Act Density 0.156%

    No Known Activations