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

    Neuronpedia

    INDEX
    Explanations

    Summaries and conclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Went
    -0.07
     knobs
    -0.07
     Amnesty
    -0.06
    안내
    -0.06
    	dialog
    -0.06
    廳
    -0.06
     Shopify
    -0.06
     hashtag
    -0.06
     وكان
    -0.06
    ÜR
    -0.06
    POSITIVE LOGITS
     using
    0.06
     consume
    0.06
    HTTPRequest
    0.06
     deceptive
    0.06
     idle
    0.06
     μ
    0.06
     pared
    0.06
     double
    0.06
    double
    0.06
     Lower
    0.06
    Act Density 0.021%

    No Known Activations