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

    Neuronpedia

    INDEX
    Explanations

    cone

    np_max-act · gemini-2.0-flash

    references to specific proteins and their biochemical roles.

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

    The neuron selectively activates on uncommon, domain-specific vocabulary—especially scientific or technical terms (e.g. chemical, biological, or specialized jargon).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    たり
    -0.06
    932
    -0.06
     пут
    -0.06
    htaking
    -0.06
    황
    -0.06
    329
    -0.06
    forcement
    -0.06
    _handling
    -0.06
     prev
    -0.06
    cing
    -0.06
    POSITIVE LOGITS
     tomb
    0.07
    _retry
    0.07
     змож
    0.06
     FIRE
    0.06
    iaomi
    0.06
    .decode
    0.06
     investigators
    0.06
     GmbH
    0.06
     laughed
    0.06
     bộ
    0.06
    Act Density 0.472%

    No Known Activations