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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on concrete environment-objects and furnishings, i.e. nouns naming tangible things in the scene.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    narrative elements depicting themes of dominance and submission.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    destruct
    -0.06
    окон
    -0.06
    _Mode
    -0.06
    SUP
    -0.06
     afternoon
    -0.06
    لفة
    -0.06
    ิค
    -0.06
    FDA
    -0.06
    avoid
    -0.06
     onboard
    -0.06
    POSITIVE LOGITS
    specs
    0.07
     iv
    0.07
     Wander
    0.06
    exclude
    0.06
     zem
    0.06
     america
    0.06
    (return
    0.06
     zen
    0.06
     democracy
    0.06
     vyž
    0.06
    Act Density 0.018%

    No Known Activations