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

    Neuronpedia

    INDEX
    Explanations

    finished

    np_max-act · gemini-2.0-flash

    This neuron tends to detect longer content words (roughly six or more letters long).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    altar
    -0.07
    起こ
    -0.07
    dealloc
    -0.06
    .magic
    -0.06
    RuntimeObject
    -0.06
    啊啊
    -0.06
     TCHAR
    -0.06
    .assertIsInstance
    -0.06
    _without
    -0.06
    filer
    -0.06
    POSITIVE LOGITS
     mnemonic
    0.06
     تشکیل
    0.06
     final
    0.06
    ims
    0.06
     تقو
    0.06
     más
    0.06
     spice
    0.06
    اسه
    0.06
    ing
    0.06
     mike
    0.06
    Act Density 0.000%

    No Known Activations