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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aging
    -0.07
     flush
    -0.07
    962
    -0.06
     Sandbox
    -0.06
     Niet
    -0.06
    ег
    -0.06
     Edwards
    -0.06
    (@
    -0.06
     Thermal
    -0.06
     đầy
    -0.06
    POSITIVE LOGITS
    larını
    0.07
     Jewelry
    0.06
    swana
    0.06
     Moments
    0.06
    _playlist
    0.06
    澤
    0.06
    (PyObject
    0.06
    ........
    0.06
     gi�
    0.06
    FileNotFoundException
    0.06
    Act Density 0.166%

    No Known Activations