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

    Neuronpedia

    INDEX
    Explanations

    Empowering, Shaping, Culture, Medina

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    2.72
    ：
    2.38
    :"
    2.32
    :**
    2.31
    :</
    2.29
    :*
    2.19
    ):
    2.18
    :}
    2.14
    :\
    2.14
    ]:
    2.11
    POSITIVE LOGITS
     Edition
    0.87
    आगे
    0.75
    <start_of_image>
    0.73
     enjeux
    0.72
    <unused717>
    0.71
    edition
    0.71
    とその
    0.70
    बर्ट
    0.69
    lessons
    0.68
    それでも
    0.67
    Act Density 0.187%

    No Known Activations