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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron activates on words within the formal, highly detailed technical description sections of a patent (e.g. in device‐and‐method disclosures and figure explanations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    atak
    -0.06
     Real
    -0.06
    _GAP
    -0.06
     kredi
    -0.06
    Forms
    -0.06
    界
    -0.06
     Kidd
    -0.06
    ergency
    -0.06
    _real
    -0.05
     öner
    -0.05
    POSITIVE LOGITS
    キング
    0.08
     adamant
    0.07
     можете
    0.07
     Abort
    0.07
    _CART
    0.07
    .eth
    0.07
    arias
    0.06
    Extend
    0.06
    :///
    0.06
    (rules
    0.06
    Act Density 0.107%

    No Known Activations