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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    电
    -0.07
    ела
    -0.07
    ASSES
    -0.07
     denim
    -0.07
     margins
    -0.06
     /**↵
    -0.06
    asses
    -0.06
    -reported
    -0.06
     bull
    -0.06
    だよ
    -0.06
    POSITIVE LOGITS
    ousel
    0.07
    ฐ
    0.06
    creens
    0.06
    GraphNode
    0.06
    920
    0.06
    쟁
    0.06
     büy
    0.06
    <TSource
    0.06
     Cleaning
    0.06
    플
    0.06
    Act Density 0.451%

    No Known Activations