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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to various subjects, including percentages and monetary values

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

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.71
    parsedMessage
    -0.68
    MessageOf
    -0.66
    <unused3>
    -0.66
    <unused28>
    -0.66
    [@BOS@]
    -0.66
     kasarigan
    -0.66
     beſte
    -0.66
    <unused8>
    -0.66
    <unused14>
    -0.66
    POSITIVE LOGITS
     instead
    0.35
     res
    0.29
    instead
    0.28
    after
    0.27
    ens
    0.27
     tr
    0.26
    Res
    0.26
     after
    0.26
     ress
    0.25
    ließlich
    0.25
    Act Density 0.120%

    No Known Activations