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

    Neuronpedia

    INDEX
    Explanations

    words relating to academic literature and/or court cases, including dates and locations

    oai_token-act-pair · gemini-2.0-flash

    months of the year

    np_token-act-pair-logits · gpt-4o-mini

    Months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PhysRevLett
    -0.54
    oznam
    -0.52
    кипедия
    -0.45
    kháu
    -0.45
    izeit
    -0.44
    offsetof
    -0.44
    بوابة
    -0.44
    kheim
    -0.44
    yarnpkg
    -0.43
    ếp
    -0.43
    POSITIVE LOGITS
     April
    2.69
     July
    2.66
     September
    2.64
     June
    2.64
     March
    2.59
     October
    2.59
     February
    2.58
     August
    2.56
     December
    2.53
     November
    2.50
    Act Density 13.466%

    No Known Activations