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
     Tooltip
    -0.07
     tránh
    -0.07
    tea
    -0.06
    :";↵
    -0.06
     airplane
    -0.06
    .shtml
    -0.06
    ADMIN
    -0.06
    	rec
    -0.06
    ”↵↵
    -0.06
    itative
    -0.06
    POSITIVE LOGITS
    hr
    0.07
     kre
    0.07
     duż
    0.07
    หม
    0.07
    뷰
    0.06
     глуб
    0.06
     Ос
    0.06
     оборуд
    0.06
    (right
    0.06
    φα
    0.06
    Act Density 0.002%

    No Known Activations