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 consistently activates on numeric tokens (digits, decimals, p‐values, etc.), effectively detecting numbers within the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _yaw
    -0.07
    姐
    -0.07
    -other
    -0.07
     ViewPager
    -0.06
    amet
    -0.06
    _chg
    -0.06
    -leg
    -0.06
     powdered
    -0.06
    shirt
    -0.06
     renting
    -0.06
    POSITIVE LOGITS
    jourd
    0.07
    CTIONS
    0.07
     Africa
    0.07
    .S
    0.06
     privateKey
    0.06
    "os
    0.06
    criteria
    0.06
    ्ययन
    0.06
    .department
    0.06
    =((
    0.06
    Act Density 0.007%

    No Known Activations