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

    Neuronpedia

    INDEX
    Explanations

    request

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     graduated
    -0.08
     plat
    -0.07
     ideology
    -0.07
    grade
    -0.07
     ROI
    -0.07
     Kam
    -0.07
    -0.06
    axies
    -0.06
     Poetry
    -0.06
     đạo
    -0.06
    POSITIVE LOGITS
    (di
    0.07
    !");↵
    0.07
     DRV
    0.07
    /dis
    0.06
     guts
    0.06
     Орг
    0.06
     bodyParser
    0.06
     पहच
    0.06
    BufferData
    0.06
     midd
    0.06
    Act Density 0.004%

    No Known Activations