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

    Neuronpedia

    INDEX
    Explanations

    fray decay portray relay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ায়ন
    0.45
    airflow
    0.43
     airflow
    0.42
    िकुलर
    0.41
    ])).
    0.41
    மிழ்
    0.40
    ೀಯ
    0.39
    ार
    0.39
    ान्य
    0.38
    iyaç
    0.38
    POSITIVE LOGITS
    yyyyyyyy
    0.88
    yy
    0.79
    yyyy
    0.79
    cation
    0.74
     mắn
    0.71
    ുടെ
    0.69
    borhood
    0.59
    onnaise
    0.59
    evsky
    0.53
    ̆
    0.53
    Act Density 0.021%

    No Known Activations