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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кафед
    -0.07
     inmates
    -0.07
     příst
    -0.06
    一步
    -0.06
     forfe
    -0.06
     kittens
    -0.06
     outbreak
    -0.06
     uğ
    -0.06
     canopy
    -0.06
    组织
    -0.06
    POSITIVE LOGITS
    }&
    0.07
    $.
    0.06
     grabs
    0.06
     Roots
    0.06
    (Item
    0.06
     woodworking
    0.06
     Recognition
    0.06
    pción
    0.06
     Geometry
    0.06
     why
    0.06
    Act Density 0.000%

    No Known Activations