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

    Neuronpedia

    INDEX
    Explanations

    XML and HTML-related markup elements

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

    XML declarations and doctypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused3>
    -0.65
    [@BOS@]
    -0.65
    <unused14>
    -0.65
    <unused79>
    -0.65
    <unused41>
    -0.65
    <unused28>
    -0.65
    <unused42>
    -0.65
    <unused52>
    -0.65
    <pad>
    -0.65
    <unused17>
    -0.65
    POSITIVE LOGITS
     AssemblyCompany
    0.39
    '}';
    0.37
     interactiva
    0.28
    #![
    0.27
    <?
    0.27
    spesies
    0.26
     сухо
    0.26
    sourceType
    0.25
    setdefault
    0.25
    jsonObject
    0.24
    Act Density 0.025%

    No Known Activations