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

    Neuronpedia

    INDEX
    Explanations

    strong opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    竞选
    -0.07
     היש
    -0.07
     asian
    -0.06
    יש
    -0.06
    fontWeight
    -0.06
    /res
    -0.06
    yntaxException
    -0.06
    ダウン
    -0.06
     exig
    -0.06
    国度
    -0.06
    POSITIVE LOGITS
    俟
    0.07
    땡
    0.07
     archival
    0.07
    nergie
    0.07
    hots
    0.07
    abelle
    0.07
    Orders
    0.07
     selves
    0.07
     ali
    0.07
    سلوك
    0.06
    Act Density 0.003%

    No Known Activations