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

    Neuronpedia

    INDEX
    Explanations

    oque

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tranny
    -0.08
    .gradient
    -0.08
     survivors
    -0.07
     раст
    -0.07
    poser
    -0.07
     Bloss
    -0.07
     orb
    -0.07
    .requests
    -0.07
    leaders
    -0.07
     děti
    -0.07
    POSITIVE LOGITS
    oque
    0.10
    ackle
    0.07
    alarını
    0.06
     України
    0.06
     Courtesy
    0.06
     ном
    0.06
     suitability
    0.06
     사무
    0.06
    enuous
    0.06
     Logistics
    0.06
    Act Density 0.002%

    No Known Activations