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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     test
    -0.07
     tests
    -0.07
     timelines
    -0.07
     reports
    -0.07
     demonstration
    -0.06
     catalog
    -0.06
     transactions
    -0.06
    _PRINTF
    -0.06
     battles
    -0.06
     narrowing
    -0.06
    POSITIVE LOGITS
    ститу
    0.07
    Ensure
    0.06
    setattr
    0.06
    getPost
    0.06
     chúng
    0.06
     распред
    0.06
     ErrorMessage
    0.06
     PLEASE
    0.06
    .lucene
    0.06
    /raw
    0.06
    Act Density 0.102%

    No Known Activations