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

    Neuronpedia

    INDEX
    Explanations

    LLC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reprodu
    -0.07
    CON
    -0.07
    蜘蛛
    -0.07
    struct
    -0.07
    frame
    -0.07
    ｗｗ
    -0.07
     phạm
    -0.06
    !')↵↵
    -0.06
    rání
    -0.06
    izont
    -0.06
    POSITIVE LOGITS
     уд
    0.06
         
    0.06
    ENAME
    0.06
     hac
    0.06
     way
    0.06
     щодо
    0.06
     quart
    0.06
     hanging
    0.06
     fearful
    0.06
    imum
    0.06
    Act Density 0.001%

    No Known Activations