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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    legal or licensing terms in documentation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects license‐header version numbers, in particular the “version 2” marker.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     روش
    -0.07
    nameof
    -0.07
     فرو
    -0.07
     seaborn
    -0.06
    ноп
    -0.06
    approve
    -0.06
     국내
    -0.06
     pouch
    -0.06
     quitting
    -0.06
    حن
    -0.06
    POSITIVE LOGITS
     craftsmanship
    0.07
    izacao
    0.06
    _infos
    0.06
     unemployment
    0.06
    hips
    0.06
    igation
    0.06
    query
    0.06
     intervened
    0.06
     leadership
    0.06
    ılmaz
    0.06
    Act Density 0.001%

    No Known Activations