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

    Neuronpedia

    INDEX
    Explanations

    the skepticism, the soft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waar
    0.60
     chaque
    0.55
     제일
    0.55
    each
    0.55
     Each
    0.54
    中最
    0.53
    ैटिन
    0.53
     each
    0.52
     idag
    0.52
    είο
    0.52
    POSITIVE LOGITS
     fact
    1.68
     Tatsache
    1.52
     činjen
    1.29
     lack
    1.28
     inability
    1.25
     faptul
    1.16
    fact
    1.14
     sheer
    1.06
     extensive
    1.05
     absence
    1.03
    Act Density 0.796%

    No Known Activations