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

    Neuronpedia

    INDEX
    Explanations

    learning and enjoyment events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tx
    -0.06
    esin
    -0.06
     Police
    -0.06
    gray
    -0.06
     speeding
    -0.06
    agas
    -0.06
     governors
    -0.06
     yürüt
    -0.06
    )==
    -0.06
     burial
    -0.06
    POSITIVE LOGITS
     souha
    0.07
     requestOptions
    0.06
     �
    0.06
    (prob
    0.06
    こちら
    0.06
     ｉ
    0.06
    Ranked
    0.06
    působ
    0.06
     результ
    0.06
    (propertyName
    0.06
    Act Density 0.159%

    No Known Activations