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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。あ
    -0.06
     организма
    -0.06
    ้วย
    -0.06
    AndWait
    -0.06
    idenav
    -0.06
    	handler
    -0.06
    _group
    -0.06
     bảng
    -0.06
    oplan
    -0.06
    해보
    -0.06
    POSITIVE LOGITS
    647
    0.07
     engages
    0.07
    732
    0.07
     sess
    0.06
    .Serialize
    0.06
    .SIZE
    0.06
     (__
    0.06
    .shared
    0.06
    -",
    0.06
     gangs
    0.06
    Act Density 0.180%

    No Known Activations