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

    Neuronpedia

    INDEX
    Explanations

    documentation keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”[
    2.08
    ,”
    1.83
    ,’’
    1.73
    ”—
    1.73
     “‘
    1.67
    “.
    1.65
    ),”
    1.65
    .”
    1.64
    ?”.
    1.62
    .’’
    1.61
    POSITIVE LOGITS
     '
    1.86
     -->
    1.81
    </h3>
    1.65
    ...'
    1.65
    ↵
    1.53
     --->
    1.50
    </h2>
    1.49
     '-'
    1.45
     ('
    1.45
     :)
    1.45
    Act Density 1.838%

    No Known Activations