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

    Neuronpedia

    INDEX
    Explanations

    Math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultur
    -0.08
     vapor
    -0.08
     harvest
    -0.08
     harvesting
    -0.08
     Ding
    -0.08
    -0.08
    Genero
    -0.08
     pioneering
    -0.08
     فرهنگ
    -0.07
     Plato
    -0.07
    POSITIVE LOGITS
     phố
    0.07
     präsent
    0.07
    ंग
    0.07
    ision
    0.07
     Organisation
    0.07
    都有
    0.07
     arises
    0.07
     negeri
    0.07
     ವ್ಯಾಪ
    0.07
     Suites
    0.07
    Act Density 0.031%
    No Known Activations