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

    Neuronpedia

    INDEX
    Explanations

    generator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kö
    -0.07
     Point
    -0.06
    -code
    -0.06
     pot
    -0.06
     Wash
    -0.06
    roe
    -0.06
    روف
    -0.06
    .Lerp
    -0.06
     Tub
    -0.06
     автомоб
    -0.06
    POSITIVE LOGITS
     generator
    0.07
     DataType
    0.06
     редак
    0.06
     собствен
    0.06
     провер
    0.06
     authorize
    0.06
     полез
    0.06
    .setHeader
    0.06
     generators
    0.06
    Exclude
    0.06
    Act Density 0.005%

    No Known Activations