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

    Neuronpedia

    INDEX
    Explanations

    artificial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salary
    -0.08
    elage
    -0.07
    uration
    -0.07
    _Tab
    -0.06
     Damage
    -0.06
     Hosting
    -0.06
    eways
    -0.06
     Breakfast
    -0.06
     spaghetti
    -0.06
    oes
    -0.06
    POSITIVE LOGITS
     []↵↵↵
    0.08
     suf
    0.06
    DataURL
    0.06
    |--
    0.06
     halde
    0.06
     سریع
    0.06
     แพ
    0.06
    .↵↵↵
    0.06
    .↵↵↵↵
    0.06
     jeux
    0.06
    Act Density 0.021%

    No Known Activations