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

    Neuronpedia

    INDEX
    Explanations

    learning resources exposure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.60
    ┛
    0.60
    🔫
    0.60
     deadlock
    0.59
    waterslide
    0.58
    dise
    0.58
     लेणी
    0.57
     مکتی
    0.57
     сили
    0.57
     ninja
    0.55
    POSITIVE LOGITS
     emits
    0.50
     R
    0.48
    R
    0.47
     Emit
    0.46
     Racial
    0.46
     উদ্বেগ
    0.46
     Anime
    0.46
     Regional
    0.44
     получа
    0.43
     Emission
    0.43
    Act Density 0.002%

    No Known Activations