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

    Neuronpedia

    INDEX
    Explanations

    questions asking for confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ઉપરા
    0.36
    娲
    0.36
    ObjectUnderTest
    0.35
    ಲಿದೆ
    0.35
    яти
    0.35
    кистон
    0.35
     WPARAM
    0.34
    अव
    0.34
    Escolh
    0.34
     orale
    0.34
    POSITIVE LOGITS
     доказа
    0.48
     proof
    0.47
     outfit
    0.46
     Overall
    0.46
     proving
    0.46
     proves
    0.45
     pairings
    0.45
     definitivamente
    0.44
     Proof
    0.43
     outfits
    0.43
    Act Density 0.000%

    No Known Activations