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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens involved in reporting quantitative data—numbers, time periods, measurement statistics, and related numeric detail.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Unix
    -0.06
     gland
    -0.06
    圧
    -0.06
     Gardner
    -0.06
    Semaphore
    -0.06
     شده
    -0.06
     عباس
    -0.06
     Trap
    -0.06
    函数
    -0.06
     landsc
    -0.06
    POSITIVE LOGITS
     dostan
    0.07
    KERNEL
    0.07
    .sequence
    0.06
    ！",
    0.06
    /^
    0.06
    _NEXT
    0.06
     Oliv
    0.06
     número
    0.06
    unit
    0.06
     marketers
    0.06
    Act Density 0.048%

    No Known Activations