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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific topics

    np_max-act · gemini-2.0-flash

    This neuron responds to specialized technical or scientific terminology (e.g., “data,” “tracking,” “Networks,” “accurate,” “recognition”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     and
    -0.11
     &
    -0.09
    and
    -0.09
     AND
    -0.08
    .ship
    -0.07
    dto
    -0.06
     �
    -0.06
    _and
    -0.06
    एन
    -0.06
    -and
    -0.06
    POSITIVE LOGITS
     总
    0.06
    _scores
    0.06
    =>'
    0.06
     ↵    ↵
    0.06
    ↵                ↵
    0.06
    )
↵
↵
    0.06
    		 ↵
    0.06
    ashtra
    0.06
     حديث
    0.06
    他的
    0.06
    Act Density 0.599%

    No Known Activations