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

    Neuronpedia

    INDEX
    Explanations

    horizontal lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    픽
    -0.08
    DrawerToggle
    -0.07
     Palmer
    -0.07
    158
    -0.07
    川
    -0.07
     PEM
    -0.07
     prezident
    -0.06
     Cros
    -0.06
     magnetic
    -0.06
     Pix
    -0.06
    POSITIVE LOGITS
    ＿＿
    0.07
     millennia
    0.06
    _category
    0.06
    commons
    0.06
     tông
    0.06
    _dims
    0.06
     geliştir
    0.06
     incompetent
    0.06
    young
    0.06
    /native
    0.05
    Act Density 0.003%

    No Known Activations