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

    Neuronpedia

    INDEX
    Explanations

    tokens ending in "ut"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зва
    0.41
    锼
    0.39
    টা
    0.38
    arkt
    0.38
    㐫
    0.38
    ignée
    0.37
    용
    0.37
    曏
    0.37
    ด
    0.37
    ppard
    0.37
    POSITIVE LOGITS
    rition
    0.68
    ierrez
    0.54
    ted
    0.52
    hentication
    0.51
    crackers
    0.48
    ti
    0.47
     neutrons
    0.47
    tttt
    0.46
    ritional
    0.46
    opia
    0.45
    Act Density 0.023%

    No Known Activations