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

    Neuronpedia

    INDEX
    Explanations

    technical language related to procedural improvements and methodologies

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

    Following tokens "the", "an", or "your"

    np_acts-logits-general · gemini-2.0-flash

    current existing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !*\
    -0.73
    出版年
    -0.65
     betweenstory
    -0.62
    VersionUID
    -0.58
     /\.
    -0.57
    mazioni
    -0.53
    انيف
    -0.53
    RRect
    -0.52
    ServletConfig
    -0.50
     typelib
    -0.50
    POSITIVE LOGITS
     existing
    3.18
     current
    3.04
     currently
    2.86
     Existing
    2.72
    current
    2.72
    existing
    2.70
    Existing
    2.65
    currently
    2.57
     CURRENT
    2.50
     EXISTING
    2.49
    Act Density 0.769%

    No Known Activations