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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hashCode
    -0.07
     refriger
    -0.07
    ＿＿＿＿
    -0.06
     isFirst
    -0.06
    [start
    -0.06
     denomin
    -0.06
    iphery
    -0.06
     trưởng
    -0.06
    ]").
    -0.06
     Producer
    -0.06
    POSITIVE LOGITS
     LANG
    0.06
    urchases
    0.06
     DA
    0.06
    URAL
    0.06
    stocks
    0.06
     Pek
    0.06
     Jail
    0.06
     Clarence
    0.06
     USA
    0.06
    -added
    0.06
    Act Density 0.058%

    No Known Activations