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

    Neuronpedia

    INDEX
    Explanations

    accuracy in aviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    രംഭ
    1.03
     તે
    0.98
    0.87
     السعود
    0.85
    ه‌ای
    0.85
    りは
    0.85
    های
    0.84
    ه‌ی
    0.82
    のア
    0.82
    スキー
    0.81
    POSITIVE LOGITS
    0
    1.42
    2
    1.19
    8
    1.19
    9
    1.09
    ↵
    1.04
    6
    0.96
    5
    0.92
    ments
    0.91
    ou
    0.89
    ill
    0.88
    Act Density 0.063%

    No Known Activations