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

    Neuronpedia

    INDEX
    Explanations

    Please ensure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ：
    0.44
    沉
    0.43
     .
    0.42
    疑
    0.42
    ‌.
    0.42
    哪些
    0.41
    θαν
    0.41
    embed
    0.41
    깼
    0.40
    otf
    0.39
    POSITIVE LOGITS
     endearing
    0.48
     державної
    0.45
     ณ
    0.43
     endurance
    0.43
     cheering
    0.43
     jogging
    0.43
     ذریعے
    0.43
     coupling
    0.42
     Soccer
    0.42
     بہترین
    0.42
    Act Density 0.045%

    No Known Activations