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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fruits
    0.48
     bouquets
    0.47
     banners
    0.46
     puffs
    0.45
     ayl
    0.45
     slain
    0.45
     legumes
    0.44
     polysaccharides
    0.44
     sterility
    0.44
     erectile
    0.44
    POSITIVE LOGITS
    8
    0.54
    de
    0.52
    re
    0.49
    ра
    0.46
    6
    0.46
    9
    0.46
    STUD
    0.43
    优先级
    0.43
    ேயே
    0.43
     পারা
    0.43
    Act Density 0.000%

    No Known Activations