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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of athletes’ participation in specific Olympic (and similar) competitions by spotting the “at <year> Summer/Paralympics” category strings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Weekly
    -0.06
     rude
    -0.06
     jul
    -0.06
    .dom
    -0.06
    [Test
    -0.06
    　�
    -0.06
    -int
    -0.05
     ['-
    -0.05
     doit
    -0.05
     веч
    -0.05
    POSITIVE LOGITS
    :indexPath
    0.07
    ?",↵
    0.07
    sleep
    0.07
     precautions
    0.07
    .temperature
    0.07
     chaining
    0.06
     normalize
    0.06
    开始
    0.06
     career
    0.06
     posture
    0.06
    Act Density 0.002%

    No Known Activations