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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    This neuron primarily detects occurrences of the question word “Why.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    payload
    -0.07
    (news
    -0.07
    	angle
    -0.06
     кого
    -0.06
     payload
    -0.06
     foreach
    -0.06
     simulation
    -0.06
    acoes
    -0.06
    .documentElement
    -0.06
     помощи
    -0.06
    POSITIVE LOGITS
    ibling
    0.07
     defy
    0.07
     vests
    0.07
    vio
    0.06
     علت
    0.06
     irrig
    0.06
     Factor
    0.06
    čila
    0.06
     Kop
    0.06
     sebeb
    0.06
    Act Density 0.027%

    No Known Activations