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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to programming and software development

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

    server proxy http URL uri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    -0.47
    .
    -0.41
     
    -0.39
     s
    -0.39
    1
    -0.38
    -
    -0.38
    ,
    -0.38
    [
    -0.38
    0
    -0.38
     (
    -0.38
    POSITIVE LOGITS
    ValueStyle
    1.06
     ModelExpression
    0.98
    <unused14>
    0.93
    <pad>
    0.92
    <unused51>
    0.92
    <unused16>
    0.92
    <unused42>
    0.92
    <unused28>
    0.92
    [@BOS@]
    0.92
    <unused3>
    0.92
    Act Density 0.648%

    No Known Activations