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

    Neuronpedia

    INDEX
    Explanations

    function or method

    np_max-act · gemini-2.0-flash

    The neuron fires on words that talk about invoking or defining code routines—i.e. “call,” “function,” or “method.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     performance
    -0.07
     lapse
    -0.07
    _rule
    -0.07
     Integrity
    -0.06
    kp
    -0.06
     за
    -0.06
    .AutoComplete
    -0.06
    amiento
    -0.06
     awareness
    -0.06
    scenario
    -0.06
    POSITIVE LOGITS
    া
    0.07
    *i
    0.07
     망
    0.06
    هل
    0.06
    _Window
    0.06
    دن
    0.06
    �
    0.06
     Plugins
    0.06
    庄
    0.06
    عف
    0.06
    Act Density 0.035%

    No Known Activations