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

    Neuronpedia

    INDEX
    Explanations

    html meta tags and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สุด
    0.36
    MDEw
    0.35
    你
    0.35
     arī
    0.35
    ين
    0.34
    شارة
    0.34
    id
    0.34
     også
    0.33
    NYC
    0.33
    ඳ
    0.33
    POSITIVE LOGITS
     Technische
    0.43
     こちら
    0.41
     Евро
    0.40
     һәм
    0.40
     carboxyl
    0.40
     використа
    0.40
     борьбе
    0.39
    ↵
    0.39
     ಕಾಂಗ್ರೆ
    0.38
     формирование
    0.38
    Act Density 0.045%

    No Known Activations