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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fat
    -0.07
    Ｂ
    -0.07
    Apps
    -0.06
    <r
    -0.06
    -trained
    -0.06
     Birds
    -0.06
    约
    -0.06
    =is
    -0.06
    .attrs
    -0.06
    -for
    -0.06
    POSITIVE LOGITS
    ้องก
    0.08
     Maison
    0.08
     Düz
    0.08
     mö
    0.07
    atég
    0.06
    есто
    0.06
     mosques
    0.06
     ble
    0.06
    coupon
    0.06
     errorThrown
    0.06
    Act Density 0.005%

    No Known Activations