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

    Neuronpedia

    INDEX
    Explanations

    sep

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals—especially floating‐point numbers—in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CString
    -0.07
    世界
    -0.07
     fiction
    -0.07
     isinstance
    -0.06
    (integer
    -0.06
     ท
    -0.06
    cluding
    -0.06
    _batch
    -0.06
     Locke
    -0.06
    =============↵
    -0.06
    POSITIVE LOGITS
     SAP
    0.07
     RegExp
    0.06
    (Color
    0.06
     소리
    0.06
     кли
    0.06
     Yelp
    0.06
     webcam
    0.06
     sep
    0.06
    ervas
    0.06
     app
    0.06
    Act Density 0.002%

    No Known Activations