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

    Neuronpedia

    INDEX
    Explanations

    Negative consequences/warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reyes
    -0.07
     pressed
    -0.07
     lingerie
    -0.07
     راه
    -0.07
     trục
    -0.06
     polic
    -0.06
    :a
    -0.06
     rendition
    -0.06
     rendering
    -0.06
    (xml
    -0.06
    POSITIVE LOGITS
    _Details
    0.06
     PRIMARY
    0.06
     Би
    0.06
    aze
    0.06
    MainWindow
    0.06
    .setVertical
    0.06
    keywords
    0.06
    antaged
    0.06
     unge
    0.05
     проводить
    0.05
    Act Density 0.176%

    No Known Activations