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

    Neuronpedia

    INDEX
    Explanations

    -based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cons
    -0.07
    маг
    -0.07
     spoken
    -0.07
    сі
    -0.07
     ores
    -0.07
     designed
    -0.07
     النهاية
    -0.07
     endet
    -0.07
     overlap
    -0.07
     partial
    -0.07
    POSITIVE LOGITS
     headquartered
    0.10
    -ja
    0.10
    总部
    0.09
    住
    0.09
     gevestigd
    0.09
     multinational
    0.09
     sedent
    0.09
     habitantes
    0.09
     headquarters
    0.09
     specializing
    0.08
    Act Density 0.014%

    No Known Activations