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

    Neuronpedia

    INDEX
    Explanations

    women

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of women in the context of their social roles, status, or rights.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    яти
    -0.07
    struction
    -0.07
    imals
    -0.06
    Vect
    -0.06
    rms
    -0.06
     एल
    -0.06
    Server
    -0.06
     skepticism
    -0.06
    �
    -0.06
    表示
    -0.06
    POSITIVE LOGITS
    (tr
    0.08
    spy
    0.07
    =_('
    0.07
    "}
    0.07
    :\\
    0.06
    (ball
    0.06
    (mc
    0.06
     jav
    0.06
     etmiş
    0.06
     Concurrent
    0.06
    Act Density 0.031%

    No Known Activations