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

    Neuronpedia

    INDEX
    Explanations

    Republic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moses
    -0.07
    غيل
    -0.07
     gre
    -0.06
    ität
    -0.06
    Hu
    -0.06
    하다
    -0.06
    Sur
    -0.06
     walker
    -0.06
     zoo
    -0.06
    JWT
    -0.06
    POSITIVE LOGITS
     vectors
    0.07
    558
    0.06
    ahr
    0.06
     FAIL
    0.06
    cores
    0.06
     Hornets
    0.06
     Vulkan
    0.06
    ，看
    0.06
    (separator
    0.06
    DUCT
    0.06
    Act Density 0.027%

    No Known Activations