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

    Neuronpedia

    INDEX
    Explanations

    percentages and quantity

    np_max-act · gemini-2.0-flash

    The neuron fires on numerical tokens—digits, percentages, or numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Private
    -0.07
     lỗ
    -0.06
     lecturer
    -0.06
    .addTab
    -0.06
     STRICT
    -0.06
    Monkey
    -0.06
    Patient
    -0.06
     uma
    -0.06
     Brake
    -0.06
     -/↵
    -0.06
    POSITIVE LOGITS
     dazz
    0.07
    .clock
    0.06
     мінім
    0.06
    لع
    0.06
     NaN
    0.06
     벽
    0.06
    cpp
    0.06
    �
    0.06
    점
    0.06
    ฤ
    0.06
    Act Density 0.158%

    No Known Activations