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

    Neuronpedia

    INDEX
    Explanations

    he or she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    625
    -0.07
    (unittest
    -0.07
     δη
    -0.06
    ’t
    -0.06
    าร
    -0.06
    _HANDLE
    -0.06
     juin
    -0.06
    611
    -0.06
     пенс
    -0.06
    quiries
    -0.06
    POSITIVE LOGITS
    owe
    0.07
     Francie
    0.06
    Tile
    0.06
     Che
    0.06
     Hugo
    0.06
    /sw
    0.06
     صرف
    0.06
     undes
    0.06
    [current
    0.06
     desc
    0.06
    Act Density 0.073%

    No Known Activations