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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron flags personal names (especially party names, often appellants) in legal document headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    revolution
    -0.08
    phen
    -0.07
    aste
    -0.07
     Tue
    -0.06
     exc
    -0.06
     maxim
    -0.06
     promoter
    -0.06
    _barrier
    -0.06
     Monter
    -0.06
     siè
    -0.06
    POSITIVE LOGITS
     fm
    0.07
    ्डल
    0.07
     casi
    0.07
     acne
    0.06
    ble
    0.06
     �
    0.06
    ('__
    0.06
     الأم
    0.06
     الف
    0.06
     KeyEvent
    0.06
    Act Density 0.009%

    No Known Activations