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

    Neuronpedia

    INDEX
    Explanations

    UE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzo
    -0.07
    Cols
    -0.06
    ско
    -0.06
     nap
    -0.06
     chy
    -0.06
     prv
    -0.06
    cers
    -0.06
    риз
    -0.06
    носи
    -0.06
    评价
    -0.06
    POSITIVE LOGITS
    ?option
    0.07
     <!
    0.06
     Wars
    0.06
     instructed
    0.06
     Dominion
    0.06
    026
    0.06
     Marines
    0.06
    (mail
    0.06
    .Security
    0.06
    qli
    0.06
    Act Density 0.005%

    No Known Activations