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

    Neuronpedia

    INDEX
    Explanations

    references to contemporary context or current events

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

    modern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.49
     crash
    -0.44
     OFDb
    -0.43
     crashes
    -0.41
    PostInfinity
    -0.41
     crashing
    -0.38
    writeFieldEnd
    -0.37
    deja
    -0.36
     ExecuteAsync
    -0.36
     typelib
    -0.36
    POSITIVE LOGITS
    delwed
    0.50
     modernes
    0.50
     modernos
    0.49
    MODERN
    0.48
    woordig
    0.48
    GEBURTSDATUM
    0.47
     modern
    0.47
    Modern
    0.47
    modern
    0.46
    今では
    0.44
    Act Density 0.076%

    No Known Activations