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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taxes
    -0.07
    .Save
    -0.06
    /compiler
    -0.06
     accomplish
    -0.06
    .AddInParameter
    -0.06
    内容
    -0.06
    企
    -0.06
     ú
    -0.06
     stagnant
    -0.06
    lığın
    -0.06
    POSITIVE LOGITS
     WX
    0.08
    ้าง
    0.07
    SCRIPT
    0.06
    нього
    0.06
     Subway
    0.06
    highest
    0.06
    igure
    0.06
    ................................................................
    0.06
    ITUDE
    0.06
    extern
    0.06
    Act Density 0.014%

    No Known Activations