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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron detects decimal numbers (fractional values, especially percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Clazz
    -0.07
    学校
    -0.07
    ướ
    -0.07
    (training
    -0.06
    response
    -0.06
    Firefox
    -0.06
    公里
    -0.06
     complex
    -0.06
    ΩΝ
    -0.06
     сигн
    -0.06
    POSITIVE LOGITS
    (le
    0.07
    cha
    0.06
     palm
    0.06
     перемен
    0.06
    IFO
    0.06
    (EC
    0.06
    Ｅ
    0.06
     :|:
    0.06
     clarity
    0.06
    ring
    0.06
    Act Density 0.014%

    No Known Activations