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

    Neuronpedia

    INDEX
    Explanations

    Code/Software hooks

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of programming‐style type or class identifiers (especially Java/Java‐like CamelCase names and imported class names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    itor
    -0.08
    cca
    -0.07
    ene
    -0.06
    	ap
    -0.06
    apture
    -0.06
    Customer
    -0.06
    ck
    -0.06
     Estr
    -0.06
    .AreEqual
    -0.06
     user
    -0.06
    POSITIVE LOGITS
    ,),↵
    0.07
    -gray
    0.07
     Dummy
    0.06
    Lt
    0.06
     المص
    0.06
    _behavior
    0.06
     tears
    0.06
     xxx
    0.06
    BundleOrNil
    0.06
    /**/*.
    0.06
    Act Density 0.053%

    No Known Activations