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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron activates on text describing how to perform an “Insert in a nested list without expanding it” operation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	cell
    -0.07
    ceph
    -0.07
    ites
    -0.06
     setPosition
    -0.06
    meeting
    -0.06
     gor
    -0.06
     Stre
    -0.06
    pressure
    -0.06
    =======↵
    -0.06
    Rol
    -0.06
    POSITIVE LOGITS
     мають
    0.07
     материал
    0.07
    值
    0.07
     inconsistent
    0.06
     mbedtls
    0.06
    finish
    0.06
    (Search
    0.06
     bitwise
    0.06
     inconsistencies
    0.06
    _rest
    0.06
    Act Density 0.069%

    No Known Activations