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

    Neuronpedia

    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Relative
    -0.07
    _disconnect
    -0.06
     Adjustment
    -0.06
    connection
    -0.06
    .Run
    -0.06
    combination
    -0.06
    Detection
    -0.06
    Certificate
    -0.06
    per
    -0.06
    Hands
    -0.06
    POSITIVE LOGITS
     quem
    0.08
    .setData
    0.07
    рует
    0.07
     Stam
    0.07
     sass
    0.06
    setData
    0.06
     exports
    0.06
    gorit
    0.06
     dağı
    0.06
    setQuery
    0.06
    Act Density 0.032%

    No Known Activations