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

    Neuronpedia

    INDEX
    Explanations

    the indefinite article "a" in various contexts

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

    a descriptive phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.76
     Infórmanos
    -0.73
    webElementXpaths
    -0.71
    parsedMessage
    -0.70
    featureID
    -0.68
    Personendaten
    -0.65
     ligiloj
    -0.62
    SourceChecksum
    -0.60
    writeFieldEnd
    -0.58
    참고
    -0.57
    POSITIVE LOGITS
     chain
    0.39
    /******/
    0.38
     unui
    0.38
     split
    0.36
     structured
    0.35
     via
    0.35
     framework
    0.35
     setas
    0.35
     interaction
    0.34
     mandate
    0.34
    Act Density 0.081%

    No Known Activations