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

    Neuronpedia

    INDEX
    Explanations

    list items separated by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    会将
    0.46
    ное
    0.42
     स्‍
    0.41
     conducta
    0.40
    ãos
    0.39
    љи
    0.39
    ந்த
    0.38
    чики
    0.38
    ේෂ
    0.38
     cuz
    0.38
    POSITIVE LOGITS
     Plus
    0.47
     Proceeds
    0.47
     प्लस
    0.43
     Also
    0.43
    also
    0.43
     Ibid
    0.42
     Subscription
    0.42
    available
    0.41
     supplemented
    0.41
     Kato
    0.41
    Act Density 0.000%

    No Known Activations