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

    Neuronpedia

    INDEX
    Explanations

    healthcare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Camera
    -0.07
    cannot
    -0.07
     clue
    -0.07
    advance
    -0.07
     ,,
    -0.07
    不僅
    -0.07
    checks
    -0.07
    :s
    -0.07
     pipelines
    -0.07
     evidently
    -0.06
    POSITIVE LOGITS
    调节
    0.07
    ())->
    0.07
     пря
    0.07
     pedal
    0.07
    뤼
    0.07
    num
    0.07
    עשייה
    0.07
    ектор
    0.07
     curry
    0.06
    OC
    0.06
    Act Density 0.054%

    No Known Activations