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

    Neuronpedia

    INDEX
    Explanations

    educational games

    np_max-act · gemini-2.0-flash

    The neuron detects instructional or explanatory language—terms related to teaching, learning, explaining, or providing safety/educational guidance.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ö
    -0.07
     datastore
    -0.06
    arParams
    -0.06
    럴
    -0.06
    izarre
    -0.06
    _:*
    -0.06
    gregator
    -0.06
     trium
    -0.06
     Igor
    -0.06
     revelations
    -0.06
    POSITIVE LOGITS
    時に
    0.07
    ☴
    0.07
    (ne
    0.06
     Sample
    0.06
     Vari
    0.06
     not
    0.06
    ],↵
    0.06
     unpaid
    0.06
     concerned
    0.06
     amber
    0.06
    Act Density 0.089%

    No Known Activations