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

    Neuronpedia

    INDEX
    Explanations

    Python dataframes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Serv
    -0.07
     '#{
    -0.06
    Integrated
    -0.06
    orph
    -0.06
    Response
    -0.06
     neighbouring
    -0.06
     Integrated
    -0.06
    -associated
    -0.06
    ourses
    -0.06
    065
    -0.06
    POSITIVE LOGITS
     حالة
    0.06
    :start
    0.06
    `}↵
    0.06
    EX
    0.06
    ighet
    0.06
    伸
    0.06
     ölç
    0.06
     nex
    0.06
    äter
    0.06
    ")},↵
    0.06
    Act Density 0.007%

    No Known Activations