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

    Neuronpedia

    INDEX
    Explanations

    optional

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “optional.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	snprintf
    -0.08
     hit
    -0.06
     climbs
    -0.06
    _maximum
    -0.06
    -hit
    -0.06
    vergence
    -0.06
     FUNCTION
    -0.06
    Close
    -0.06
    ження
    -0.06
    elsif
    -0.06
    POSITIVE LOGITS
     optional
    0.10
    optional
    0.08
    (optional
    0.08
     odds
    0.07
    ?><?
    0.07
    ɵ
    0.07
    .aut
    0.07
     même
    0.07
    Optional
    0.07
     Oxford
    0.07
    Act Density 0.005%

    No Known Activations