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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with health-related topics and inquiries

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

    Three-letter abbreviations

    np_acts-logits-general · gemini-2.0-flash

    initial word segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.31
     ―――――
    -1.24
     myſelf
    -1.21
    󠁴
    -1.18
     Jefus
    -1.12
     المعيارى
    -1.12
     Efq
    -1.11
     Monfieur
    -1.11
     pleaſure
    -1.08
     Houſe
    -1.05
    POSITIVE LOGITS
    <eos>
    0.86
     
    0.79
    co
    0.67
     P
    0.63
    i
    0.62
     A
    0.62
    ↵↵
    0.61
    l
    0.61
    ))
    0.60
    n
    0.60
    Act Density 1.110%

    No Known Activations