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

    Neuronpedia

    INDEX
    Explanations

    "Applied Blindly"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.61
     \
    0.59
    you
    0.58
    5
    0.56
     you
    0.50
    ن
    0.48
    use
    0.48
    1
    0.48
    ~
    0.48
    mu
    0.47
    POSITIVE LOGITS
    ได้อย่าง
    0.52
    óż
    0.49
     cậu
    0.48
     După
    0.48
    🕜
    0.47
    捚
    0.47
     πάντα
    0.47
    ❌
    0.47
     Однако
    0.46
     întreb
    0.46
    Act Density 0.003%

    No Known Activations