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

    Neuronpedia

    INDEX
    Explanations

    aris

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whose
    -0.06
    TCP
    -0.06
    имость
    -0.06
     WITH
    -0.06
    (Rect
    -0.06
    ोफ
    -0.06
     hg
    -0.06
    까지
    -0.06
    ยาว
    -0.06
     EIF
    -0.06
    POSITIVE LOGITS
     Writers
    0.06
    Coefficient
    0.06
    ForKey
    0.06
    ่ต
    0.06
     konus
    0.06
    -msg
    0.06
    Dirs
    0.06
     urg
    0.06
    076
    0.06
    swiper
    0.06
    Act Density 0.928%

    No Known Activations