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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers

    np_max-act · gemini-2.0-flash

    The neuron detects ordinal season counts (e.g. “57th,” “41st,” “32nd”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     farms
    -0.08
    pleasant
    -0.07
     flipping
    -0.07
     mortgages
    -0.06
     forCellReuseIdentifier
    -0.06
     ethanol
    -0.06
     dbs
    -0.06
    Paginator
    -0.06
    .getBoundingClientRect
    -0.06
     concatenate
    -0.06
    POSITIVE LOGITS
     Дон
    0.07
     мир
    0.06
     synchronized
    0.06
    .obj
    0.06
     olduk
    0.06
    .ipv
    0.06
    ounding
    0.06
    Unix
    0.06
     Θεσσα
    0.05
     }}">
    0.05
    Act Density 0.006%

    No Known Activations