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

    Neuronpedia

    INDEX
    Explanations

    code paths ending/slashes

    np_max-act · gemini-2.0-flash

    This neuron fires on inline code comments (text following “#” that describe an instruction or note).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    敷
    -0.06
     ظرفیت
    -0.06
    ανά
    -0.06
    mekte
    -0.06
     Draco
    -0.06
    际
    -0.06
     コ
    -0.06
     prefect
    -0.06
    inic
    -0.06
    _ED
    -0.06
    POSITIVE LOGITS
     dakika
    0.07
     tweet
    0.07
    tableName
    0.07
    IOException
    0.06
    .Sql
    0.06
    	trigger
    0.06
    JI
    0.06
     Suriye
    0.06
    .ObjectId
    0.06
    -Fi
    0.06
    Act Density 0.014%

    No Known Activations