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

    Neuronpedia

    INDEX
    Explanations

    negative comparisons or feelings regarding individuals or groups

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

    preceding names or descriptions of people

    np_acts-logits-general · gemini-2.0-flash

    describing people and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.77
     kasarigan
    -0.66
     gainera
    -0.66
    Демографія
    -0.63
    RenderAtEndOf
    -0.61
    Geplaatst
    -0.61
     >=",
    -0.60
    keyColumn
    -0.60
     umani
    -0.58
    kmäler
    -0.58
    POSITIVE LOGITS
     Proven
    0.55
     veck
    0.54
     learned
    0.54
     enfans
    0.54
    名は
    0.53
    learned
    0.53
     unfortunate
    0.52
    posedge
    0.51
     pageNo
    0.51
     poor
    0.50
    Act Density 0.379%

    No Known Activations