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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly those of notable individuals and public figures

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

    Names followed by a last name or title

    np_acts-logits-general · gemini-2.0-flash

    first names followed by surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.55
    MemoryWarning
    -0.54
     صوتيه
    -0.52
    ViewFeatures
    -0.50
     OFDb
    -0.48
    ImageContext
    -0.48
     rhestr
    -0.48
     escra
    -0.45
    trường
    -0.45
     peeps
    -0.44
    POSITIVE LOGITS
     spokesman
    0.71
    BeginContext
    0.65
    transQ
    0.63
     كومونز
    0.61
    gameserver
    0.61
     spokesperson
    0.58
     deputy
    0.58
    rungsseite
    0.58
    RegressionTest
    0.56
    Santis
    0.56
    Act Density 0.170%

    No Known Activations