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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     examples
    -0.07
    unittest
    -0.07
    ertext
    -0.06
     του
    -0.06
    htt
    -0.06
     estimator
    -0.06
     Neural
    -0.06
    Clear
    -0.06
    .getBytes
    -0.06
     petroleum
    -0.06
    POSITIVE LOGITS
    がい
    0.07
    jin
    0.07
     outlet
    0.07
    :k
    0.06
    coli
    0.06
    pagen
    0.06
     لل
    0.06
     olur
    0.06
    feb
    0.06
    _method
    0.06
    Act Density 0.021%

    No Known Activations