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

    Neuronpedia

    INDEX
    Explanations

    Russian suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     לראש
    -0.08
    ตาราง
    -0.07
    _VALUES
    -0.06
    _aa
    -0.06
    -testid
    -0.06
    Twig
    -0.06
    تكون
    -0.06
    "struct
    -0.06
    ADDRESS
    -0.06
    luğun
    -0.06
    POSITIVE LOGITS
     Casual
    0.08
     Forced
    0.07
    啪
    0.07
    遗留
    0.07
     Raj
    0.07
    锖
    0.07
     Matrix
    0.07
     ctx
    0.07
    法官
    0.06
     poorer
    0.06
    Act Density 0.054%

    No Known Activations