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

    Neuronpedia

    INDEX
    Explanations

    others

    np_max-act · gemini-2.0-flash

    This neuron detects generalizing quantifier words—especially tokens like “others,” “more,” and “many” that refer to additional unspecified items.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FromString
    -0.07
     parked
    -0.07
    ))))↵↵
    -0.06
    area
    -0.06
    	show
    -0.06
     travellers
    -0.06
    게시
    -0.06
     анг
    -0.06
    ][-
    -0.06
     života
    -0.06
    POSITIVE LOGITS
     opr
    0.07
    ตอบ
    0.07
    егда
    0.06
     Aydın
    0.06
    ğe
    0.06
     Covered
    0.06
    Noise
    0.06
     野
    0.06
    (primary
    0.05
    numberOf
    0.05
    Act Density 0.027%

    No Known Activations