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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of language (and related terms like script), flagging whenever the text discusses a specific language or writing system.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    luck
    -0.07
     dynamically
    -0.06
    	items
    -0.06
    unicorn
    -0.06
     travels
    -0.06
     jer
    -0.06
     Colts
    -0.06
     жив
    -0.06
     طی
    -0.06
    าช
    -0.06
    POSITIVE LOGITS
    TableViewCell
    0.07
    rotein
    0.07
    educated
    0.06
    indows
    0.06
    _pixels
    0.06
    روم
    0.06
     composing
    0.06
     cellphone
    0.06
     pourrait
    0.06
    ])
    0.06
    Act Density 0.031%

    No Known Activations