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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    code related to software licensing and copyright information.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on code identifiers that name teardown or cleanup operations—imperative verbs in method names like destroy, release, unregister, cleanup, stop, unmount, disable, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    冰
    -0.07
     ط
    -0.07
    ��
    -0.07
    梁
    -0.06
     ріш
    -0.06
    شته
    -0.06
    墨
    -0.06
    舉
    -0.06
    قع
    -0.06
    دام
    -0.06
    POSITIVE LOGITS
     OMG
    0.06
     Australian
    0.06
     dlouho
    0.06
     omp
    0.06
    MethodBeat
    0.06
    Throwable
    0.06
    abyrinth
    0.06
    ????
    0.06
    rai
    0.06
    Scala
    0.06
    Act Density 0.032%

    No Known Activations