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

    Neuronpedia

    INDEX
    Explanations

    the term "Indian" in various contexts

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

    indian nationality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McCabe
    -0.48
     Rowe
    -0.48
    ause
    -0.47
    parallax
    -0.46
     Corbett
    -0.46
     Whyte
    -0.46
    otta
    -0.46
    via
    -0.45
    BindView
    -0.45
     Catalyst
    -0.45
    POSITIVE LOGITS
     Indian
    1.95
    Indian
    1.91
     indian
    1.71
    indian
    1.66
     INDIAN
    1.60
     Indians
    1.40
    INDIAN
    1.40
    Indians
    1.23
     भारतीय
    1.01
     indios
    0.88
    Act Density 0.010%

    No Known Activations