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

    Neuronpedia

    INDEX
    Explanations

    Hi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Venezuela
    -0.07
    Robot
    -0.07
     Melbourne
    -0.07
    Andre
    -0.07
     labels
    -0.07
    NN
    -0.07
    漂流
    -0.07
     עבור
    -0.07
    .moveToNext
    -0.07
    美洲
    -0.06
    POSITIVE LOGITS
    🔂
    0.08
    тор
    0.07
    팟
    0.07
    蒋介
    0.07
    開發
    0.07
    薄膜
    0.07
    ものは
    0.06
     chairs
    0.06
    ⓚ
    0.06
    activated
    0.06
    Act Density 0.011%

    No Known Activations