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

    Neuronpedia

    INDEX
    Explanations

    best all-around guess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     кіль
    0.45
    籌
    0.44
    こういう
    0.40
     ಚಿ
    0.40
    kal
    0.39
     ಗುರು
    0.39
     тексту
    0.39
     ಪಡೆ
    0.39
    ον
    0.38
     вигля
    0.38
    POSITIVE LOGITS
     حساس
    0.38
     Safari
    0.38
     weekdays
    0.38
     defined
    0.37
     lube
    0.37
     weekday
    0.37
     মাধ্যমিক
    0.37
     grande
    0.36
     midd
    0.36
    Webhook
    0.36
    Act Density 0.000%

    No Known Activations