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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apsed
    -0.07
     practiced
    -0.06
    Enabled
    -0.06
    demand
    -0.06
    OUTPUT
    -0.06
    umbled
    -0.06
     reaches
    -0.06
     considers
    -0.06
     repeatedly
    -0.06
     discouraged
    -0.06
    POSITIVE LOGITS
     leg
    0.07
     jes
    0.07
    $item
    0.07
     rowspan
    0.07
     เล
    0.07
     "-"
    0.07
    productId
    0.06
    $_['
    0.06
    ो
    0.06
     +#+#+#+#+#+
    0.06
    Act Density 0.015%

    No Known Activations