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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on programming-style tokens—keywords, identifiers, and syntax (like function names, operators, and brackets)—i.e. snippets of code rather than ordinary prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    reated
    -0.07
     بخش
    -0.07
    rov
    -0.07
    .dynamic
    -0.07
    な
    -0.07
     Fiction
    -0.07
     Вели
    -0.06
    	TEST
    -0.06
     некотор
    -0.06
    plus
    -0.06
    POSITIVE LOGITS
     ¬
    0.06
     finger
    0.06
     Bölüm
    0.06
    Lifecycle
    0.06
    _ENTER
    0.06
     chr
    0.06
     viewWillAppear
    0.06
     Hedge
    0.06
     GR
    0.06
    _IND
    0.06
    Act Density 0.078%

    No Known Activations