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

    Neuronpedia

    INDEX
    Explanations

    specific keyword usage contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İlçesi
    0.49
    按下
    0.46
     restante
    0.46
     বাঁধবেন
    0.45
    Ი
    0.44
     Direktor
    0.42
    న్స్‌
    0.42
    籿
    0.42
    Ე
    0.42
    噪音
    0.41
    POSITIVE LOGITS
    -
    0.53
    ,
    0.45
    erving
    0.43
     in
    0.41
    .
    0.41
    ian
    0.40
    ↵
    0.39
    銀
    0.38
     ሂደ
    0.37
    ).
    0.37
    Act Density 0.000%

    No Known Activations