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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly related to organizations, names, and specific terms in a scientific context

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

    sucrose, Whirlpool, Nehru, zodiac signs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onOptions
    -0.68
    FunctionFlags
    -0.65
    dafx
    -0.62
     propOrder
    -0.62
     '\\;'
    -0.62
    aarrggbb
    -0.60
    脚注の使い方
    -0.59
    complexContent
    -0.58
    RegressionTest
    -0.57
    TokenNameLPAREN
    -0.57
    POSITIVE LOGITS
    座
    1.34
     Hobart
    1.01
     座
    0.95
    住
    0.76
     Whirlpool
    0.66
     住
    0.60
    坐
    0.59
     whirlpool
    0.57
    rlpool
    0.56
     Suc
    0.55
    Act Density 0.007%

    No Known Activations