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

    Neuronpedia

    INDEX
    Explanations

    code and punctuation boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    트
    0.42
     editions
    0.41
    س
    0.41
    aire
    0.40
    。
    0.40
     normal
    0.40
     allere
    0.40
    seit
    0.39
    ه‌ها
    0.39
    liability
    0.39
    POSITIVE LOGITS
    Atl
    0.46
     {}>,
    0.45
     ))}
    0.44
    欱
    0.44
     HttpSession
    0.44
     અન્ય
    0.42
    カートリッジ
    0.42
     Nomor
    0.42
     Однако
    0.42
    ()");
    0.42
    Act Density 0.000%

    No Known Activations