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

    Neuronpedia

    INDEX
    Explanations

    parentheses and brackets

    np_max-act · gemini-2.0-flash

    The neuron fires on the Java lambda arrow “->,” i.e. it detects lambda expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     liar
    -0.07
     taxes
    -0.06
    getService
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
     HttpStatus
    -0.06
    ManagerInterface
    -0.06
    _save
    -0.06
    strlen
    -0.06
    .Inject
    -0.06
    -www
    -0.06
    POSITIVE LOGITS
    advert
    0.07
    Const
    0.07
     гра
    0.07
     transistor
    0.07
     Mini
    0.06
    _New
    0.06
     ascertain
    0.06
     عل
    0.06
     extremist
    0.06
     pthread
    0.06
    Act Density 0.006%

    No Known Activations