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

    Neuronpedia

    INDEX
    Explanations

    technical specifications

    np_max-act · gemini-2.0-flash

    This neuron primarily detects the coordinating word “or.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ène
    -0.07
     developers
    -0.07
     doma
    -0.06
     abdomen
    -0.06
    institution
    -0.06
    related
    -0.06
     greatest
    -0.06
     Athena
    -0.06
    真正
    -0.06
     executes
    -0.06
    POSITIVE LOGITS
    .cli
    0.07
    icultural
    0.06
    /info
    0.06
     disadv
    0.06
    989
    0.06
    -remove
    0.06
    _pitch
    0.06
    Inventory
    0.06
    herit
    0.06
     inhab
    0.06
    Act Density 0.061%

    No Known Activations