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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetSize
    -0.06
     #{
    -0.06
    되는
    -0.06
    (long
    -0.06
    (te
    -0.06
    _YES
    -0.06
                    ↵
    -0.06
    sha
    -0.06
     TResult
    -0.06
    ','',
    -0.06
    POSITIVE LOGITS
     PAY
    0.07
     مص
    0.07
     direct
    0.07
    .dev
    0.07
     Alan
    0.06
    Sn
    0.06
     Freight
    0.06
     Dram
    0.06
     τις
    0.06
     Jessie
    0.06
    Act Density 0.014%

    No Known Activations