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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or editions of publications

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

    days and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pe
    -0.41
    1
    -0.40
    b
    -0.37
    ac
    -0.37
    me
    -0.36
    ca
    -0.36
    qrstuvwxyz
    -0.36
    al
    -0.36
    berg
    -0.35
    common
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.77
     Tuesday
    0.73
     Tuesdays
    0.71
     Wednesday
    0.69
     Monday
    0.68
     Fridays
    0.66
     Mondays
    0.66
    posedge
    0.66
    Tuesday
    0.66
    <unused7>
    0.65
    Act Density 0.033%

    No Known Activations