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

    Neuronpedia

    INDEX
    Explanations

    legal and research documents

    np_max-act · gemini-2.0-flash

    The neuron is spotting lines prefixed with the “#” character (comment or quoted lines).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    calculator
    -0.07
     Gew
    -0.07
    浴
    -0.07
    dealloc
    -0.07
     glEnd
    -0.07
     �
    -0.07
     dane
    -0.06
     dsp
    -0.06
     购
    -0.06
     报
    -0.06
    POSITIVE LOGITS
     emergencies
    0.07
    _advanced
    0.06
    (messages
    0.06
     terrorism
    0.06
    )],↵
    0.06
     documentary
    0.06
    �
    0.06
    Hunter
    0.06
     Farm
    0.06
    銷
    0.06
    Act Density 0.059%

    No Known Activations