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

    Neuronpedia

    INDEX
    Explanations

    verbs

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to action words—i.e. lexical verbs denoting processes or operations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ,total
    -0.07
     added
    -0.07
     three
    -0.06
     Boh
    -0.06
     couldn
    -0.06
    Nr
    -0.06
     dried
    -0.06
     ł
    -0.06
    Ca
    -0.06
     šť
    -0.06
    POSITIVE LOGITS
    Connect
    0.09
    Assign
    0.08
    Convert
    0.08
    Upload
    0.07
     Kill
    0.07
    Persist
    0.07
    喝
    0.07
     Print
    0.07
     weave
    0.07
    (connect
    0.07
    Act Density 0.347%

    No Known Activations