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

    Neuronpedia

    INDEX
    Explanations

    guidance for calculations and estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antitumor
    0.39
    মর
    0.38
    ወዳ
    0.38
     perfeito
    0.38
    টিয়ে
    0.38
     türlü
    0.38
    ক্রান্ত
    0.37
     pravo
    0.37
     acumen
    0.36
     gelişmeler
    0.36
    POSITIVE LOGITS
     Example
    0.45
     S
    0.43
     D
    0.43
     simpler
    0.43
     Consider
    0.41
    voorbeeld
    0.41
    １
    0.40
     consider
    0.40
     Consid
    0.40
     P
    0.39
    Act Density 0.001%

    No Known Activations