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

    Neuronpedia

    INDEX
    Explanations

    listing diverse items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     koncent
    0.28
     üç
    0.28
     Gün
    0.26
     trzy
    0.26
     fünf
    0.26
     enzim
    0.25
     König
    0.24
     três
    0.24
     décadas
    0.24
     trei
    0.24
    POSITIVE LOGITS
    、
    0.30
    或
    0.28
    bm
    0.25
    や
    0.25
    等等
    0.25
    ד
    0.25
    adien
    0.24
    $,
    0.24
    과
    0.24
    dis
    0.24
    Act Density 0.606%

    No Known Activations