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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or absence

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

    Followed by "more," "longer", or similar comparatives

    np_acts-logits-general · gemini-2.0-flash

    some more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.93
    "}")
    -0.83
     للاسماء
    -0.82
    webElementXpaths
    -0.78
     Roskov
    -0.77
    bootstrapcdn
    -0.76
     وتسجيلات
    -0.76
    اریخ
    -0.74
     disambiguazione
    -0.68
    UnusedPrivate
    -0.68
    POSITIVE LOGITS
     more
    0.52
     sort
    0.51
    how
    0.49
     kind
    0.49
    more
    0.48
    bod
    0.47
    ones
    0.47
     particular
    0.47
    thing
    0.46
    place
    0.46
    Act Density 0.208%

    No Known Activations