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

    Neuronpedia

    INDEX
    Explanations

    authorhip and ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уда
    0.43
     చిహ్
    0.41
    क्षण
    0.40
    ancı
    0.39
    ொள்
    0.39
    isopropyl
    0.38
    வோ
    0.38
    ícul
    0.37
     reemplazar
    0.37
    ಂಕ
    0.37
    POSITIVE LOGITS
     author
    0.50
    Author
    0.46
    Автор
    0.46
    author
    0.45
     Author
    0.42
    barrier
    0.39
     Planung
    0.39
     disp
    0.38
     autora
    0.38
     تیس
    0.38
    Act Density 0.000%

    No Known Activations