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

    Neuronpedia

    INDEX
    Explanations

    really common or important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estómago
    0.41
    ኦ
    0.40
     luxuri
    0.39
    是非
    0.39
    헉
    0.39
    iado
    0.38
    otiti
    0.38
    豪华
    0.38
     kleinere
    0.38
    ialize
    0.37
    POSITIVE LOGITS
     Quite
    0.49
     Insight
    0.49
     perce
    0.45
     percep
    0.43
     sharp
    0.42
     HPV
    0.41
     Fund
    0.41
     fund
    0.40
     Hale
    0.40
     പോലെ
    0.40
    Act Density 0.012%

    No Known Activations