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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "more."

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

    additional quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ExecuteAsync
    -0.52
     BrowserModule
    -0.50
    LEGGI
    -0.47
    GenerationType
    -0.47
    cyklopedia
    -0.46
     nisso
    -0.45
    RTEX
    -0.45
    RTHOOK
    -0.45
    ationen
    -0.45
    RSpec
    -0.44
    POSITIVE LOGITS
    Another
    0.75
     Another
    0.74
    another
    0.72
     additional
    0.72
     another
    0.69
    additional
    0.69
     ANOTHER
    0.68
     ADDITIONAL
    0.62
    Additional
    0.62
     Additional
    0.61
    Act Density 0.006%

    No Known Activations