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

    Neuronpedia

    INDEX
    Explanations

    ive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Night
    -0.06
    party
    -0.06
    esda
    -0.06
    	then
    -0.06
    ј
    -0.06
    █
    -0.06
    !).
    -0.06
     精
    -0.06
     bog
    -0.06
    LO
    -0.06
    POSITIVE LOGITS
     Research
    0.07
     Article
    0.07
     συ
    0.07
     winnings
    0.07
     dönem
    0.06
     ksi
    0.06
    цип
    0.06
     امنیت
    0.06
     cyc
    0.06
     Bazı
    0.06
    Act Density 0.009%

    No Known Activations