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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and colons, often indicating function definitions or parameters in code

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

    programming language context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vnd
    -0.33
     “
    -0.31
    ly
    -0.31
     indeed
    -0.30
     ost
    -0.29
     Angeb
    -0.29
     vor
    -0.28
     "
    -0.28
    <h1>
    -0.28
    <strong>
    -0.28
    POSITIVE LOGITS
     AssemblyCulture
    0.76
    verwijspagina
    0.75
    Personendaten
    0.72
    ftagPool
    0.69
    EDEFAULT
    0.66
    tagHelperRunner
    0.66
    CloseOperation
    0.64
     dezelve
    0.63
    ValueStyle
    0.63
     InputDecoration
    0.63
    Act Density 0.002%

    No Known Activations