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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Menu
    -0.07
    ーフ
    -0.07
     reservoir
    -0.07
    YSTICK
    -0.06
    YTE
    -0.06
     command
    -0.06
     physicist
    -0.06
    stp
    -0.06
     manifold
    -0.06
    105
    -0.06
    POSITIVE LOGITS
     Immediate
    0.08
     України
    0.07
     Burg
    0.07
     Федера
    0.06
    uces
    0.06
    (Array
    0.06
     Wy
    0.06
     Perm
    0.06
    lichkeit
    0.06
    Brit
    0.06
    Act Density 0.128%

    No Known Activations