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

    Neuronpedia

    INDEX
    Explanations

    legal texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cairo
    -0.08
     Mango
    -0.07
     dataSet
    -0.07
    xmax
    -0.07
     ginger
    -0.07
     Infant
    -0.07
    狗
    -0.07
     mỏi
    -0.07
     Ramirez
    -0.07
     Goblin
    -0.07
    POSITIVE LOGITS
    ...(
    0.08
    -/
    0.08
    Resolved
    0.08
    [(
    0.07
    -(
    0.07
    的历史
    0.07
    -[
    0.07
     oral
    0.07
     hacked
    0.06
     ...(
    0.06
    Act Density 0.128%

    No Known Activations