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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash

    This neuron detects negative imperatives in the rules (phrases like “Do not include any…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rahat
    -0.07
    -oriented
    -0.06
     tanks
    -0.06
     shouted
    -0.06
     cáo
    -0.06
    }`}>↵
    -0.06
    ивает
    -0.06
     аналіз
    -0.06
    -0.06
    quist
    -0.06
    POSITIVE LOGITS
    _mr
    0.06
     LC
    0.06
     exig
    0.06
     식
    0.06
    نام
    0.06
     PL
    0.06
    (Event
    0.06
    JSONException
    0.06
    olia
    0.06
    .isEnabled
    0.06
    Act Density 0.012%

    No Known Activations