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

    Neuronpedia

    INDEX
    Explanations

    numbers in millions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ดี๋ยว
    0.49
    aisesti
    0.47
     нравится
    0.43
     anharmonic
    0.43
     flirting
    0.42
     Holistic
    0.42
     flirt
    0.42
     inflex
    0.42
     ticked
    0.42
     erkannt
    0.42
    POSITIVE LOGITS
     million
    1.71
     thousand
    1.62
    million
    1.49
    thousand
    1.44
     millón
    1.32
     Million
    1.31
    Million
    1.29
     lakh
    1.27
     مليون
    1.26
     millions
    1.25
    Act Density 0.353%

    No Known Activations