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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Archbishop
    -0.06
     shipment
    -0.06
     Rek
    -0.06
    	con
    -0.06
     standards
    -0.06
     expressions
    -0.06
    _within
    -0.06
     constituted
    -0.06
    벌
    -0.06
    京
    -0.06
    POSITIVE LOGITS
     yüzden
    0.07
    098
    0.06
    ensburg
    0.06
    (ins
    0.06
     omdat
    0.06
     Scar
    0.06
    اسي
    0.06
    _RGCTX
    0.06
    __,↵
    0.06
     vrch
    0.06
    Act Density 0.020%

    No Known Activations