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

    Neuronpedia

    INDEX
    Explanations

    AI models and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ження
    0.47
    erebbe
    0.43
     Узбеки
    0.43
    Nasdaq
    0.43
    లూ
    0.43
     एंप
    0.43
    zij
    0.42
     líng
    0.42
    สาม
    0.42
     inasmuch
    0.42
    POSITIVE LOGITS
    ك
    0.50
    ک
    0.46
    농
    0.46
    Ти
    0.45
    頖
    0.44
     श्रे
    0.43
     antiques
    0.43
    𝑻
    0.43
    किस
    0.43
    କ
    0.42
    Act Density 0.507%

    No Known Activations