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

    Neuronpedia

    INDEX
    Explanations

    misunderstand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ラン
    -0.07
    柯
    -0.07
     bỏ
    -0.07
    Im
    -0.07
     because
    -0.06
    נם
    -0.06
     blossom
    -0.06
    leh
    -0.06
    له
    -0.06
    ظن
    -0.06
    POSITIVE LOGITS
     sạn
    0.08
    cter
    0.07
     talked
    0.07
    赒
    0.06
    quia
    0.06
     pours
    0.06
    🎆
    0.06
    ☋
    0.06
    خبر
    0.06
    (author
    0.06
    Act Density 0.035%

    No Known Activations