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

    Neuronpedia

    INDEX
    Explanations

    references to programming functions and commands

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

    function calls and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.16
     queſta
    -1.07
    MigrationBuilder
    -1.05
    <unused28>
    -1.03
    <unused8>
    -1.02
    <unused3>
    -1.02
    <unused14>
    -1.02
    <unused16>
    -1.02
    <pad>
    -1.02
    [@BOS@]
    -1.02
    POSITIVE LOGITS
    (
    0.65
     (
    0.60
    （
    0.44
    ()
    0.37
     on
    0.36
     using
    0.36
    [
    0.36
    ('
    0.36
     for
    0.35
     at
    0.33
    Act Density 0.041%

    No Known Activations