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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric expressions—tokens that are digits or number-related (e.g. dates, times, quantities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    اف
    -0.07
     multim
    -0.07
     discrimination
    -0.07
     neurons
    -0.07
    инув
    -0.07
     furniture
    -0.07
     Ct
    -0.07
    汽车
    -0.07
     and
    -0.06
     computing
    -0.06
    POSITIVE LOGITS
    .MouseEvent
    0.07
    こちら
    0.07
     heatmap
    0.06
    heatmap
    0.06
    .LatLng
    0.06
     {$
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    lesai
    0.06
    #{@
    0.06
     sayılı
    0.06
    Act Density 0.043%

    No Known Activations