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

    Neuronpedia

    INDEX
    Explanations

    code syntax and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ys
    0.75
    0.72
    謖
    0.70
    ことを
    0.70
    qu
    0.69
    ts
    0.69
    si
    0.68
    cannot
    0.67
    şey
    0.67
    te
    0.67
    POSITIVE LOGITS
     הנ
    0.83
    کرات
    0.77
    ి
    0.76
     interoper
    0.74
     chatId
    0.72
    ൺ
    0.71
     ৷
    0.70
     ∣
    0.70
     Ayurved
    0.68
     ▸
    0.68
    Act Density 0.001%

    No Known Activations