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

    Neuronpedia

    INDEX
    Explanations

    sequence of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     искусство
    0.40
    。
    0.36
    Begriffsklär
    0.35
     Гульнявыя
    0.35
    ΕΙ
    0.34
    Кор
    0.34
     истори
    0.34
    Ი
    0.34
     ιστο
    0.33
    ։
    0.33
    POSITIVE LOGITS
     ataupun
    0.45
    かもしれませんが
    0.44
     huidige
    0.43
     attuale
    0.43
     maupun
    0.43
     sempat
    0.43
     iż
    0.42
     atuais
    0.41
     mentioning
    0.41
     jedynie
    0.40
    Act Density 0.000%

    No Known Activations