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

    Neuronpedia

    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tester
    -0.08
    world
    -0.08
     decorated
    -0.08
     Number
    -0.07
     Activities
    -0.07
     Girls
    -0.07
     cards
    -0.07
     party
    -0.07
     signal
    -0.07
     Cards
    -0.07
    POSITIVE LOGITS
    　　 　 　
    0.07
    ально
    0.07
    ‬
    0.07
    ¤¤
    0.06
     Inline
    0.06
     derail
    0.06
    (inplace
    0.06
    翻
    0.06
    　　　 　 　
    0.06
    　 　 　 　
    0.06
    Act Density 0.004%

    No Known Activations