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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecs
    -0.08
    ylie
    -0.07
    admins
    -0.07
    альном
    -0.07
    hooks
    -0.07
    avery
    -0.07
    цез
    -0.06
     seating
    -0.06
     turns
    -0.06
     bathrooms
    -0.06
    POSITIVE LOGITS
     bipolar
    0.07
     фундамент
    0.06
     협
    0.06
     chorus
    0.06
    gel
    0.06
     nomin
    0.06
     fract
    0.06
     khổ
    0.06
     구조
    0.06
     lợi
    0.06
    Act Density 0.001%

    No Known Activations