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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Engine
    -0.07
     بلکه
    -0.06
    оком
    -0.06
     Grinder
    -0.06
    _INCREMENT
    -0.06
    (My
    -0.06
    .Pr
    -0.06
    іст
    -0.06
    .He
    -0.06
     fossils
    -0.06
    POSITIVE LOGITS
     Merge
    0.06
     doprav
    0.06
    /problems
    0.06
     algum
    0.06
    :f
    0.06
     :↵↵↵↵
    0.06
    باح
    0.06
     rushes
    0.06
    ']):
    0.06
    abee
    0.06
    Act Density 0.000%

    No Known Activations