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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uniform
    -0.07
     lý
    -0.06
     дух
    -0.06
    娘
    -0.06
     každé
    -0.06
     sessuali
    -0.06
     comport
    -0.06
    ิทย
    -0.06
     їх
    -0.06
     Hun
    -0.06
    POSITIVE LOGITS
     설명
    0.07
     famously
    0.07
     OkHttpClient
    0.07
    [__
    0.06
    "id
    0.06
     AssemblyTrademark
    0.06
    วโม
    0.06
    ordova
    0.06
    sters
    0.06
    .Items
    0.06
    Act Density 0.140%

    No Known Activations