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

    Neuronpedia

    INDEX
    Explanations

    mixed topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    族的
    0.58
    したいと思います
    0.58
    ुलिस
    0.55
    伢
    0.55
    쿱
    0.54
    लेक्ट्र
    0.53
    ത്തര
    0.53
    Popover
    0.53
    本当
    0.52
     આવેલા
    0.52
    POSITIVE LOGITS
     dahulu
    0.66
     wa
    0.60
     membr
    0.60
     Watson
    0.58
    elast
    0.57
    bal
    0.57
     jen
    0.57
     lagi
    0.56
     conditioning
    0.56
     ops
    0.56
    Act Density 0.000%

    No Known Activations