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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash

    This neuron primarily detects the pronoun “it.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hin
    -0.07
     EventBus
    -0.06
    Abr
    -0.06
    住
    -0.06
     المم
    -0.06
     biệt
    -0.06
    
    -0.06
    SSERT
    -0.06
     причин
    -0.06
    kode
    -0.06
    POSITIVE LOGITS
    ''↵
    0.08
     blow
    0.07
    	engine
    0.07
     Components
    0.06
    !")↵
    0.06
     SRC
    0.06
    .Clone
    0.06
    ':↵
    0.06
     dissoci
    0.06
    在线阅读
    0.06
    Act Density 0.179%

    No Known Activations