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

    Neuronpedia

    INDEX
    Explanations

    tuple definition or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗥
    2.47
    อร์
    2.26
    𝗸
    2.25
    𝘆
    2.22
    𝗮
    2.21
    𝗹
    2.17
    𝘀
    2.13
    étendue
    2.13
     else
    2.11
    ➝
    2.08
    POSITIVE LOGITS
    р
    2.44
    ಪಡ
    2.25
    ような
    2.18
     dignitaries
    2.05
    े
    2.05
    ο
    1.94
    an
    1.94
    ভাবে
    1.91
    و
    1.90
    ా
    1.88
    Act Density 0.045%

    No Known Activations