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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幸せ
    -0.08
    овым
    -0.07
    旆
    -0.07
     owes
    -0.07
    Ẓ
    -0.06
    咦
    -0.06
    Ⓝ
    -0.06
     lend
    -0.06
    @app
    -0.06
    pół
    -0.06
    POSITIVE LOGITS
     "");
    0.07
    身體
    0.07
     //<
    0.07
     demons
    0.06
    missing
    0.06
     magazines
    0.06
     Walker
    0.06
     comp
    0.06
    Weight
    0.06
    ected
    0.06
    Act Density 0.135%

    No Known Activations