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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    actual
    -0.07
    เกม
    -0.06
    Modify
    -0.06
     DISP
    -0.06
    epoch
    -0.06
     produ
    -0.06
     ук
    -0.06
     )
↵
    -0.06
    modal
    -0.06
     ва
    -0.06
    POSITIVE LOGITS
    .GONE
    0.07
     зміст
    0.07
     能
    0.06
    /AP
    0.06
    cciones
    0.06
    菜
    0.06
    敬
    0.06
     України
    0.06
    .MiddleCenter
    0.06
    bine
    0.06
    Act Density 0.006%

    No Known Activations