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

    Neuronpedia

    INDEX
    Explanations

    sameness or equality

    np_max-act · gemini-2.0-flash

    This neuron fires on phrases describing equal or uniform distribution—especially constructions like “same amount,” “roughly the same,” or “uses roughly the same time.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /down
    -0.07
     Vertex
    -0.07
    overn
    -0.06
     Express
    -0.06
    	Map
    -0.06
     Molecular
    -0.06
    �
    -0.06
     ビ
    -0.06
     sentencing
    -0.06
     Assault
    -0.06
    POSITIVE LOGITS
     még
    0.07
     Нет
    0.07
    yd
    0.07
    gien
    0.07
    του
    0.06
    使
    0.06
     سعود
    0.06
     towels
    0.06
     Stake
    0.06
    ]string
    0.06
    Act Density 0.036%

    No Known Activations