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

    Neuronpedia

    INDEX
    Explanations

    both, all, and except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Você
    0.42
     Sometimes
    0.39
     নাকি
    0.38
    憔
    0.37
     ছুঁ
    0.36
     You
    0.36
    被称为
    0.35
     Bước
    0.35
     você
    0.35
     TikTok
    0.35
    POSITIVE LOGITS
     zarówno
    0.50
     সকলেই
    0.48
     except
    0.48
     ಎಲ್ಲಾ
    0.46
    oltre
    0.45
     excepting
    0.44
    除
    0.44
    except
    0.43
    both
    0.43
     所有
    0.41
    Act Density 0.027%

    No Known Activations