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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ESV
    -0.07
    isc
    -0.07
     ",",
    -0.06
     mensen
    -0.06
    .authorization
    -0.06
    !');↵
    -0.06
     filmed
    -0.06
    %",↵
    -0.06
     Speech
    -0.06
    .')↵
    -0.06
    POSITIVE LOGITS
     decking
    0.07
     abroad
    0.07
    兰
    0.07
    BERS
    0.07
    260
    0.06
     vista
    0.06
    .scheduler
    0.06
    jedn
    0.06
    ầng
    0.06
     unexpected
    0.06
    Act Density 0.100%

    No Known Activations