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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PARATOR
    -0.07
    삷
    -0.07
     }.
    -0.07
    ',↵↵
    -0.07
    gen
    -0.07
    ñ
    -0.07
    Score
    -0.07
    тив
    -0.07
     البن
    -0.07
    %(
    -0.06
    POSITIVE LOGITS
     Magento
    0.08
     Innovation
    0.07
     straw
    0.07
     iterations
    0.07
    有一种
    0.07
     investing
    0.07
     eagle
    0.07
     blade
    0.07
     Hunters
    0.06
     Painting
    0.06
    Act Density 0.025%

    No Known Activations