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

    Neuronpedia

    INDEX
    Explanations

    explicit sexual content and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     მათ
    0.45
     explicitly
    0.36
    utérus
    0.35
    வற்றை
    0.35
     trusty
    0.35
     비슷
    0.34
    it
    0.34
    संख्यक
    0.34
    ública
    0.34
    িকভাবে
    0.34
    POSITIVE LOGITS
    An
    0.30
    AI
    0.30
    COMP
    0.29
    нис
    0.29
    ﾘ
    0.29
     I
    0.28
    AG
    0.28
     outlay
    0.28
    Quarter
    0.28
    Bud
    0.27
    Act Density 0.331%

    No Known Activations