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

    Neuronpedia

    INDEX
    Explanations

    Gender

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “gender” (often as a heading or key topic label).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pies
    -0.08
    -line
    -0.08
     Note
    -0.07
    it
    -0.07
    ioc
    -0.07
    Acts
    -0.07
     onc
    -0.06
    ooks
    -0.06
    Streamer
    -0.06
    at
    -0.06
    POSITIVE LOGITS
     gender
    0.16
    Gender
    0.14
     Gender
    0.14
    gender
    0.09
    _gender
    0.09
     Geld
    0.09
     transgender
    0.09
     genders
    0.08
     geld
    0.08
     sex
    0.08
    Act Density 0.007%

    No Known Activations