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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.09
     HttpURLConnection
    -0.07
    🐊
    -0.07
    圫
    -0.07
    洞
    -0.07
    睑
    -0.07
     sleepy
    -0.07
     Martinez
    -0.07
     señor
    -0.07
     HinderedRotor
    -0.07
    POSITIVE LOGITS
     xy
    0.07
    فق
    0.07
    فر
    0.07
     TEM
    0.07
     frequency
    0.06
     우
    0.06
     DAT
    0.06
     hundreds
    0.06
     REQUIRE
    0.06
    原始
    0.06
    Act Density 0.006%

    No Known Activations