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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and specific identifiers in scientific or technical contexts

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

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.68
     ſte
    -0.65
     varandra
    -0.59
     fubject
    -0.56
     ſch
    -0.54
     deſt
    -0.53
     poffe
    -0.53
     purpoſe
    -0.53
     anſ
    -0.52
    uxxxx
    -0.52
    POSITIVE LOGITS
    eleven
    0.54
     Eleven
    0.52
     المعيارى
    0.52
    Eleven
    0.50
    Twelve
    0.47
     Eleventh
    0.45
     eleven
    0.45
     Twelve
    0.45
     ten
    0.44
    Eight
    0.44
    Act Density 0.451%

    No Known Activations