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

    Neuronpedia

    INDEX
    Explanations

    model identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leukocytes
    0.66
     proinflammatory
    0.64
     adrenergic
    0.63
     truncated
    0.62
    superclass
    0.62
    genesis
    0.62
    Technology
    0.62
     surmounted
    0.61
    asthen
    0.61
     overlapped
    0.61
    POSITIVE LOGITS
    вими
    0.69
    fighting
    0.68
     NAMES
    0.64
    olge
    0.64
    йте
    0.64
     ট্রেনে
    0.64
    тивным
    0.64
    Lets
    0.64
    ჷ
    0.64
    Ự
    0.63
    Act Density 0.009%

    No Known Activations