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

    Neuronpedia

    INDEX
    Explanations

    symbols and terms related to specific demographics or identities

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

    person/people (all languages)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iomanip
    -0.52
     theat
    -0.41
     SUSTAIN
    -0.40
     leaps
    -0.37
    alis
    -0.36
     Maynard
    -0.36
     ativa
    -0.35
    Xls
    -0.35
    meau
    -0.35
    wußt
    -0.34
    POSITIVE LOGITS
     người
    2.22
     Người
    1.71
    người
    1.70
    Người
    1.66
     nguoi
    1.36
    ผู้
    0.99
    คน
    0.98
    people
    0.83
     people
    0.83
     ผู้
    0.81
    Act Density 0.000%

    No Known Activations