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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     registered
    -0.07
    数十
    -0.07
     Dj
    -0.07
    .TextInput
    -0.07
    Datum
    -0.07
    随着
    -0.07
    List
    -0.07
     некоторые
    -0.06
    Este
    -0.06
     PACKET
    -0.06
    POSITIVE LOGITS
    薸
    0.07
    🆓
    0.07
    ohana
    0.07
    (queue
    0.07
    育儿
    0.06
    erland
    0.06
    عرب
    0.06
     трав
    0.06
    actices
    0.06
     ?>↵↵
    0.06
    Act Density 0.065%

    No Known Activations