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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron fires on sequences of digits (numeric literals), for example version numbers or years.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    圳
    -0.07
    )f
    -0.06
     perpetrators
    -0.06
     migrating
    -0.06
    cdc
    -0.06
    descending
    -0.06
     pel
    -0.06
    -f
    -0.06
     leveled
    -0.06
     perder
    -0.06
    POSITIVE LOGITS
    _BAR
    0.07
     которой
    0.07
     جهت
    0.07
    /query
    0.07
    ,arg
    0.07
    aska
    0.06
     Exhaust
    0.06
    時に
    0.06
     постро
    0.06
    ="./
    0.06
    Act Density 0.005%

    No Known Activations