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

    Neuronpedia

    INDEX
    Explanations

    came

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handles
    -0.07
    cube
    -0.07
     Swiss
    -0.07
     cooperate
    -0.07
     temperatura
    -0.07
    goods
    -0.07
    sburg
    -0.07
    poss
    -0.06
     cunt
    -0.06
    (operation
    -0.06
    POSITIVE LOGITS
    中华民族
    0.08
    !)
    0.08
     Christianity
    0.07
    裢
    0.07
    )(*
    0.07
     chain
    0.07
     retire
    0.07
     segment
    0.07
    !");
    0.06
    深度
    0.06
    Act Density 0.001%

    No Known Activations