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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values and calculations related to totals and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    total, sum, max, new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.54
    ].
    -0.53
    ".
    -0.50
    ",
    -0.48
    >,
    -0.47
    >.
    -0.44
    </u>
    -0.44
    .
    -0.44
    ).
    -0.43
    /.
    -0.43
    POSITIVE LOGITS
    ########.
    1.03
    tagHelperRunner
    0.90
    parsedMessage
    0.88
     تضيفلها
    0.83
    ValueStyle
    0.82
     Diſ
    0.82
    tagHelper
    0.81
    Przypisy
    0.80
    BASEPATH
    0.79
     createState
    0.78
    Act Density 0.086%

    No Known Activations