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

    Neuronpedia

    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash

    This neuron detects “Definitions” (and related glossary‐style) section headers or terms indicating a definitions/glossary section.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Should
    -0.06
    需
    -0.06
    	object
    -0.06
    /'+
    -0.06
    notice
    -0.06
    โป
    -0.06
     Mã
    -0.06
    ยนต
    -0.06
    .Buffer
    -0.06
    _need
    -0.06
    POSITIVE LOGITS
    (sr
    0.07
     definitions
    0.07
     developments
    0.07
    issional
    0.06
     Johnston
    0.06
     أع
    0.06
    issance
    0.06
    \system
    0.06
     definition
    0.06
     систему
    0.06
    Act Density 0.029%

    No Known Activations