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

    Neuronpedia

    INDEX
    Explanations

    scores or ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$-(
    0.42
    ipramine
    0.41
     extremos
    0.40
     immunological
    0.39
    Imidazole
    0.38
    ikannya
    0.37
     اقبال
    0.36
    ঙ্কের
    0.36
    াড়ার
    0.36
    сіі
    0.36
    POSITIVE LOGITS
     Maybe
    0.46
    +
    0.46
    ↵↵
    0.46
    ️⃣
    0.44
     because
    0.44
     เพราะ
    0.43
     Two
    0.43
     Because
    0.42
     bởi
    0.41
    ـ
    0.41
    Act Density 0.053%

    No Known Activations