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

    Neuronpedia

    INDEX
    Explanations

    sequence of numbers or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лла
    1.25
    ت
    1.20
    т
    1.18
    أ
    1.16
    Ти
    1.15
    정
    1.15
    ро
    1.13
    ಇ
    1.13
    не
    1.11
    Ле
    1.09
    POSITIVE LOGITS
    ul
    1.11
    ,'
    1.10
    (\
    1.09
    ati
    1.05
    aucune
    1.04
    }$
    1.02
    Bris
    1.01
    }?
    1.00
    ்கள்
    1.00
    }])
    0.99
    Act Density 0.121%

    No Known Activations