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

    Neuronpedia

    INDEX
    Explanations

    directions/instructions

    np_max-act · gemini-2.0-flash

    The neuron is specifically activated by occurrences of the word “prompt.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ар
    -0.07
     Preston
    -0.07
    iên
    -0.07
    arie
    -0.07
     Facilities
    -0.07
     Vancouver
    -0.07
    Has
    -0.07
     facilities
    -0.07
     obligation
    -0.06
    Tom
    -0.06
    POSITIVE LOGITS
    \xd
    0.06
    }));↵
    0.06
    _TRY
    0.06
    _UNS
    0.06
    =[↵
    0.06
     ju
    0.06
    0.06
    ]=$
    0.06
     بسي
    0.06
    @Resource
    0.06
    Act Density 0.002%

    No Known Activations