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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .IM
    -0.07
    勋章
    -0.07
    的努力
    -0.06
     ממ
    -0.06
    DateTime
    -0.06
     بم
    -0.06
     للغاية
    -0.06
    Pdf
    -0.06
    橥
    -0.06
    펴
    -0.06
    POSITIVE LOGITS
    quipment
    0.07
    special
    0.07
    sold
    0.07
    	Field
    0.07
     perman
    0.07
    -spacing
    0.07
     relatively
    0.07
     chlorine
    0.07
     puck
    0.07
    оля
    0.07
    Act Density 0.031%

    No Known Activations