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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the exact phrase “same thing.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ama
    -0.06
    ์)
    -0.06
    Hola
    -0.06
     một
    -0.06
    _it
    -0.06
     &___
    -0.06
     apps
    -0.06
     ﺍ
    -0.06
     gatherings
    -0.06
     těla
    -0.06
    POSITIVE LOGITS
     최저
    0.07
    Concrete
    0.07
    .vertices
    0.07
     Riding
    0.07
    .only
    0.06
    と思
    0.06
    Coefficient
    0.06
    :g
    0.06
     holders
    0.06
    .calculate
    0.06
    Act Density 0.011%

    No Known Activations