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

    Neuronpedia

    INDEX
    Explanations

    quantity

    np_max-act · gemini-2.0-flash

    This neuron detects expressions of quantity or number—numerical values and count-related words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hutchinson
    -0.06
    /request
    -0.06
    Attempt
    -0.06
     Salman
    -0.06
    institution
    -0.06
     skeletons
    -0.06
    ossed
    -0.06
    非
    -0.06
     varies
    -0.06
     Worldwide
    -0.06
    POSITIVE LOGITS
     відч
    0.07
    ูป
    0.07
     прин
    0.07
    .setBorder
    0.06
    .cat
    0.06
     LAB
    0.06
     TELE
    0.06
     отправ
    0.06
    czas
    0.06
     listBox
    0.06
    Act Density 0.013%

    No Known Activations