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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustomer
    -0.07
     doomed
    -0.07
     Priest
    -0.07
    PROJECT
    -0.07
    Fran
    -0.07
     senators
    -0.06
     conclusive
    -0.06
     Guar
    -0.06
    哭
    -0.06
     Ange
    -0.06
    POSITIVE LOGITS
    Δ
    0.07
    ایع
    0.06
    ヾ
    0.06
    ạo
    0.06
    bins
    0.06
    -trade
    0.06
    RECT
    0.06
    "](
    0.06
    (_
    0.06
    	mock
    0.06
    Act Density 0.015%

    No Known Activations