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

    Neuronpedia

    INDEX
    Explanations

    commercial use and licensing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    资
    0.40
    }:
    0.37
    например
    0.36
    的说
    0.36
     snapshot
    0.35
    鲁
    0.35
     neler
    0.34
    गोलिक
    0.34
    ः
    0.34
    }
    0.33
    POSITIVE LOGITS
     यदि
    0.49
     אם
    0.48
     prohibition
    0.47
     ถ้า
    0.46
    ﹗
    0.45
    !--
    0.45
    0.43
    igarh
    0.43
    ﾊ
    0.43
     ‘’
    0.43
    Act Density 0.001%

    No Known Activations