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

    Neuronpedia

    INDEX
    Explanations

    ben names and benign terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    -2.67
     he
    -2.63
    dition
    -2.22
     modernen
    -2.20
    或者是
    -2.13
    }
    -2.09
    e
    -2.05
    z
    -2.03
     not
    -2.02
     хорошая
    -2.00
    POSITIVE LOGITS
    That
    2.97
    1
    2.91
    ଃ
    2.69
    When
    2.53
    他们在
    2.45
    2
    2.45
    當時
    2.42
    </h2>
    2.38
    那时
    2.34
    What
    2.33
    Act Density 0.018%

    No Known Activations