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

    Neuronpedia

    INDEX
    Explanations

    software tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tribut
    -0.11
     illicit
    -0.08
     Tribut
    -0.08
     chili
    -0.08
     gcd
    -0.07
     espec
    -0.07
     fermented
    -0.07
     trái
    -0.07
     spé
    -0.07
     cooled
    -0.07
    POSITIVE LOGITS
    教程
    0.17
     tutorials
    0.16
     tutorial
    0.15
    /tutorial
    0.14
    tutorial
    0.14
     Tutorial
    0.14
     anlat
    0.14
     walkthrough
    0.13
     Tutorials
    0.13
    Tutorial
    0.13
    Act Density 0.015%

    No Known Activations