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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swal
    -0.07
    ()],↵
    -0.06
     dün
    -0.06
    _trip
    -0.06
    bild
    -0.06
     tractor
    -0.06
    Given
    -0.06
    .Bl
    -0.06
    ...)↵↵
    -0.06
    对象
    -0.06
    POSITIVE LOGITS
    .Interface
    0.06
    .DEFINE
    0.06
     bankers
    0.06
    	trigger
    0.06
     مهر
    0.06
    ้าของ
    0.06
    authorization
    0.06
    	option
    0.06
    ambio
    0.06
    ż
    0.06
    Act Density 0.138%

    No Known Activations