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

    Neuronpedia

    INDEX
    Explanations

    technical writing/discussion

    np_max-act · gemini-2.0-flash

    This neuron detects German definitional phrasing—sentences that introduce or define a term (e.g. “X ist ein …,” “Die X wird …”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    information about technical subjects related to programming and software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Σα
    -0.07
    SSFWorkbook
    -0.06
    UIApplicationDelegate
    -0.06
     forecasting
    -0.06
     multip
    -0.06
    ENCES
    -0.06
    غراف
    -0.06
    lenir
    -0.05
     일어
    -0.05
    ıyorlar
    -0.05
    POSITIVE LOGITS
    MAND
    0.08
     Pleasant
    0.07
    ины
    0.06
    pg
    0.06
     arts
    0.06
    _Dec
    0.06
    itious
    0.06
    niej
    0.06
    мін
    0.06
    ossible
    0.06
    Act Density 0.206%

    No Known Activations