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

    Neuronpedia

    INDEX
    Explanations

    QA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _weights
    -0.07
     report
    -0.06
    _brand
    -0.06
    elters
    -0.06
     Report
    -0.06
     Feet
    -0.06
     transistor
    -0.06
    †
    -0.06
    Bitmap
    -0.06
    /about
    -0.06
    POSITIVE LOGITS
     QA
    0.13
    QA
    0.12
     Assurance
    0.08
     qa
    0.08
     assurance
    0.08
    qa
    0.08
    Qed
    0.07
     wherever
    0.07
    ")},↵
    0.07
    urance
    0.06
    Act Density 0.004%

    No Known Activations