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

    Neuronpedia

    INDEX
    Explanations

    command usage or dispatch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     üçüncü
    0.45
     gacchati
    0.42
     propylene
    0.42
     juf
    0.40
     ouvertes
    0.40
     clockRadius
    0.40
     brunes
    0.40
     triumphant
    0.39
     climatic
    0.39
     fruition
    0.39
    POSITIVE LOGITS
    ла
    0.45
     बातें
    0.42
    かもしれませんが
    0.42
    เจ
    0.41
     informace
    0.41
    について
    0.40
    探し
    0.40
    キャ
    0.40
     MPP
    0.40
    даг
    0.40
    Act Density 0.002%

    No Known Activations