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

    Neuronpedia

    INDEX
    Explanations

    references to influential historical figures and their contributions to ideologies or social movements

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

    after names (surnames especially)

    np_acts-logits-general · gemini-2.0-flash

    names of historical figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centerY
    -0.55
     kys
    -0.50
     unknownFields
    -0.49
    carbonyl
    -0.48
     tunggal
    -0.47
    pierw
    -0.47
    centralwidget
    -0.47
    IsContent
    -0.47
     Drittan
    -0.46
     äm
    -0.46
    POSITIVE LOGITS
     Pareto
    0.62
    DispatchToProps
    0.61
    kheim
    0.61
    twimg
    0.60
    stdc
    0.58
     Normdatei
    0.57
    iented
    0.57
     Boltzmann
    0.57
     يتيمه
    0.57
    tzmann
    0.57
    Act Density 0.205%

    No Known Activations