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

    Neuronpedia

    INDEX
    Explanations

    green

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伪造
    -0.08
     toughest
    -0.07
    стал
    -0.07
    一段时间
    -0.07
     puntos
    -0.07
    caf
    -0.07
    Reuters
    -0.07
     ############
    -0.06
    /company
    -0.06
    퀀
    -0.06
    POSITIVE LOGITS
     Family
    0.07
     attendant
    0.07
    音箱
    0.07
    ==(
    0.07
    ")->
    0.07
     dlg
    0.07
    (ic
    0.06
    lbl
    0.06
    ец
    0.06
    悲
    0.06
    Act Density 0.869%

    No Known Activations