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

    Neuronpedia

    INDEX
    Explanations

    technology performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    リーズ
    -0.07
    imentary
    -0.06
    BoundingBox
    -0.06
    phanumeric
    -0.06
    .exit
    -0.06
    по
    -0.06
    848
    -0.06
     환
    -0.06
    าต
    -0.06
    AlmostEqual
    -0.06
    POSITIVE LOGITS
     Working
    0.06
    】,
    0.06
     ProductService
    0.06
     courtesy
    0.06
     Showcase
    0.06
    Looking
    0.06
    BUR
    0.06
     Steele
    0.06
    ayı
    0.06
     rehearsal
    0.06
    Act Density 0.224%

    No Known Activations