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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soğ
    -0.07
     pup
    -0.07
     nursery
    -0.07
    ��
    -0.07
     champ
    -0.07
     place
    -0.06
     illuminate
    -0.06
    NUM
    -0.06
     Meanwhile
    -0.06
    -même
    -0.06
    POSITIVE LOGITS
    _flat
    0.07
     
↵
↵
    0.06
    getElementsByTagName
    0.06
     Hizmetleri
    0.06
     silently
    0.06
     роки
    0.06
    (quantity
    0.05
     experimenting
    0.05
     RAW
    0.05
    -threatening
    0.05
    Act Density 0.288%

    No Known Activations