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

    Neuronpedia

    INDEX
    Explanations

    period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guru
    -0.07
    getStore
    -0.06
    摆
    -0.06
     restaur
    -0.06
    (dot
    -0.06
    ується
    -0.06
    �
    -0.06
    .sequence
    -0.06
    �
    -0.06
     Whereas
    -0.06
    POSITIVE LOGITS
     Minist
    0.08
     террит
    0.07
     Doctor
    0.06
     onu
    0.06
     Downing
    0.06
     обрат
    0.06
    лся
    0.06
    atham
    0.06
     landscaping
    0.06
    朋友
    0.06
    Act Density 0.006%

    No Known Activations