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

    Neuronpedia

    INDEX
    Explanations

    (e.g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     belles
    0.06
     Brasile
    0.06
    peč
    0.05
    abline
    0.05
     sear
    0.05
     Scandinavia
    0.05
    yı
    0.04
     DefaultTargets
    0.04
     minimizing
    0.04
     skyl
    0.04
    POSITIVE LOGITS
    ຮ
    0.07
     фе
    0.07
     лише
    0.07
     வாழ்
    0.07
     सभी
    0.07
    "</
    0.07
    不是
    0.07
    ामध्ये
    0.07
    twenty
    0.07
     тільки
    0.07
    Act Density 0.076%

    No Known Activations