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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rankings and comparisons among entities or qualities

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

    "The [superlative adjective] [noun]"

    np_acts-logits-general · gemini-2.0-flash

    superlatives and uniqueness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.80
    Portale
    -0.70
     transfieras
    -0.64
    Manbalar
    -0.59
    NameInMap
    -0.58
    eol
    -0.55
    帖最后由
    -0.54
    phosa
    -0.54
     незавершена
    -0.53
    abstractmethod
    -0.52
    POSITIVE LOGITS
     most
    0.78
     strongest
    0.72
     longest
    0.71
     fastest
    0.67
     highest
    0.65
     largest
    0.63
     clearest
    0.62
     lowest
    0.60
     مرئيه
    0.59
     closest
    0.59
    Act Density 0.129%

    No Known Activations