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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Std
    -0.07
     bq
    -0.07
    fik
    -0.07
     donor
    -0.06
     whims
    -0.06
    bei
    -0.06
     Standards
    -0.06
     emitter
    -0.06
     Piet
    -0.06
    โร
    -0.06
    POSITIVE LOGITS
    apgolly
    0.06
     اصول
    0.06
    Neill
    0.06
    atherine
    0.06
    _attachment
    0.06
     yatırım
    0.06
    <pre
    0.06
    uppies
    0.06
     onTap
    0.06
     UIAlertController
    0.06
    Act Density 0.031%

    No Known Activations