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

    Neuronpedia

    INDEX
    Explanations

    URLs in markdown links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h2>
    0.87
    <strong>
    0.84
    <blockquote>
    0.81
     –,
    0.71
    0.71
    :-)
    0.68
    0.68
     -"
    0.66
     -,
    0.66
     surprise
    0.64
    POSITIVE LOGITS
    ](
    2.75
    )](
    2.05
    `](
    1.97
    ]{
    1.77
    ](#
    1.67
    ](./
    1.59
    }{\
    1.57
    ]()
    1.57
    ][
    1.56
    ](\
    1.56
    Act Density 0.075%

    No Known Activations