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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flying
    -0.07
    _barang
    -0.07
    _coupon
    -0.07
     `.
    -0.07
     nik
    -0.06
     собы
    -0.06
     hình
    -0.06
    DMETHOD
    -0.06
     Navbar
    -0.06
     고개를
    -0.06
    POSITIVE LOGITS
    Require
    0.07
     sigmoid
    0.07
     direct
    0.06
    inium
    0.06
     weak
    0.06
    ність
    0.06
    ρευ
    0.06
     batter
    0.06
     clay
    0.06
    ika
    0.06
    Act Density 0.002%

    No Known Activations