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

    Neuronpedia

    INDEX
    Explanations

    married

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of marital status, especially the word “married” (and its Russian equivalents “женат”/“жена”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ihad
    -0.07
    orte
    -0.07
     womens
    -0.07
     Hed
    -0.06
    	select
    -0.06
     SEX
    -0.06
     passages
    -0.06
     melody
    -0.06
     cdr
    -0.06
     COD
    -0.06
    POSITIVE LOGITS
    ;top
    0.07
     vyšší
    0.07
    (connectionString
    0.07
     گردش
    0.07
     علاوه
    0.06
    _ef
    0.06
    ,&
    0.06
    =nil
    0.06
    _vs
    0.06
    ्रमण
    0.06
    Act Density 0.022%

    No Known Activations