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

    Neuronpedia

    INDEX
    Explanations

    .com domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಬ್ಬಿಣ
    2.17
     dersimizde
    2.15
     দেখিতে
    2.12
    ₂,
    2.07
     videomuzda
    2.04
    ヤモンド
    2.03
     살펴보도록
    2.02
    ₁,
    2.02
    녃
    2.02
     αφού
    2.01
    POSITIVE LOGITS
    ↵
    2.78
    ↵↵
    2.46
    ↵↵↵
    2.08
    <eos>
    1.72
    )
    1.67
    ↵↵↵↵↵
    1.66
    』
    1.65
    ‬
    1.61
    </code>
    1.51
    ↵↵↵↵
    1.51
    Act Density 0.204%

    No Known Activations