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

    Neuronpedia

    INDEX
    Explanations

    version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    錵
    -3.00
    '
    -2.61
    葙
    -2.48
    this
    -2.38
    鏨
    -2.27
    you
    -2.23
    鋮
    -2.20
    warnai
    -2.20
    炻
    -2.17
    viembre
    -2.13
    POSITIVE LOGITS
    al
    2.53
    ");
    2.48
    ⢪
    2.31
    狲
    2.30
    2
    2.30
    絰
    2.28
     gefährlich
    2.28
    1
    2.27
     liberar
    2.22
    って言
    2.20
    Act Density 0.002%

    No Known Activations