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

    Neuronpedia

    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of a company’s proper name, especially chemical–industry firm names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     evaluating
    -0.07
    _resolution
    -0.07
     tracking
    -0.07
    _ATOM
    -0.07
    utar
    -0.07
     React
    -0.06
     가족
    -0.06
     wandering
    -0.06
    七
    -0.06
    _fig
    -0.06
    POSITIVE LOGITS
    (DbContext
    0.06
    ίν
    0.06
    outines
    0.06
    eurs
    0.06
     PTSD
    0.06
    aby
    0.06
    (other
    0.06
     Σχ
    0.06
     дум
    0.06
    Demand
    0.06
    Act Density 0.094%

    No Known Activations