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

    Neuronpedia

    INDEX
    Explanations

    does not or will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     正規品
    0.72
    watch
    0.72
     лигасы
    0.67
    adena
    0.67
     Lazio
    0.66
    Paris
    0.66
    Rom
    0.65
     disinvestment
    0.65
    áil
    0.64
    paris
    0.63
    POSITIVE LOGITS
     pract
    0.68
     מת
    0.61
     équipes
    0.58
     প্রান্তে
    0.55
     Pred
    0.54
     Vorte
    0.54
     Wrang
    0.52
     প্রান্ত
    0.52
    綫
    0.52
     Quantum
    0.51
    Act Density 0.133%

    No Known Activations