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

    Neuronpedia

    INDEX
    Explanations

    references to male individuals or terms associated with them

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

    people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Palmarès
    -0.44
     Normdatei
    -0.41
    ESTA
    -0.34
    нато
    -0.34
    Xoxo
    -0.34
    Tikang
    -0.33
    令
    -0.33
    anthem
    -0.33
    kath
    -0.32
    プリ
    -0.32
    POSITIVE LOGITS
     girl
    0.86
     woman
    0.85
     guy
    0.84
     lady
    0.80
     person
    0.79
     man
    0.71
     muchacha
    0.70
     pessoa
    0.69
     dude
    0.69
    eseorang
    0.69
    Act Density 0.062%

    No Known Activations