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

    Neuronpedia

    INDEX
    Explanations

    Area size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Replace
    -0.07
    (build
    -0.07
    illions
    -0.07
     등록
    -0.07
     标
    -0.06
    _mem
    -0.06
    ;//
    -0.06
    ุตสาหกรรม
    -0.06
    ιν
    -0.06
    (or
    -0.06
    POSITIVE LOGITS
     Vanity
    0.07
    چ
    0.06
     dön
    0.06
    ht
    0.06
    actors
    0.06
     condom
    0.06
     intestinal
    0.06
     віз
    0.06
     ات
    0.06
     miracle
    0.06
    Act Density 0.018%

    No Known Activations