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

    Neuronpedia

    INDEX
    Explanations

    Chemical processes

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming chemical reaction steps—especially “-ation” terms like chlorination, nitration, hydrogenation, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Matcher
    -0.07
     evacuated
    -0.06
    عات
    -0.06
    Parms
    -0.06
    TIM
    -0.06
    battery
    -0.06
     alleges
    -0.06
     Bihar
    -0.06
     recognise
    -0.06
    耐
    -0.06
    POSITIVE LOGITS
     overcoming
    0.07
    ص
    0.07
    силь
    0.07
    �
    0.07
    .al
    0.07
    .xx
    0.06
     oby
    0.06
     сост
    0.06
     المص
    0.06
     Teh
    0.06
    Act Density 0.027%

    No Known Activations