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

    Neuronpedia

    INDEX
    Explanations

    useMemo, useReducer, structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     രാ
    0.47
     przetwarz
    0.46
     नाखूनों
    0.46
    źdz
    0.44
     salariés
    0.43
    ၜ
    0.43
     الأمريكي
    0.43
     সম্পাদকীয়
    0.43
    お願い致します
    0.42
     پڑھیئے
    0.42
    POSITIVE LOGITS
    0.57
     unforgettable
    0.45
     Sending
    0.41
     there
    0.41
     Captured
    0.40
     Planet
    0.38
    arro
    0.38
     as
    0.38
     endeavour
    0.38
     dangerous
    0.37
    Act Density 0.001%

    No Known Activations