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

    Neuronpedia

    INDEX
    Explanations

    Technical reports/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Se
    -0.06
    もの
    -0.06
    enabled
    -0.06
    Benchmark
    -0.06
     дело
    -0.06
     worse
    -0.06
     bitcoin
    -0.06
     squared
    -0.06
    ládá
    -0.06
    87
    -0.06
    POSITIVE LOGITS
    urally
    0.07
     HDF
    0.06
    !");↵↵
    0.06
     Kimber
    0.06
     omas
    0.06
     tendr
    0.06
     भगव
    0.06
    slu
    0.06
    TestCase
    0.06
     एड
    0.06
    Act Density 0.307%

    No Known Activations