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

    Neuronpedia

    INDEX
    Explanations

    risk and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اں
    2.08
    ‍♂️
    1.98
    cology
    1.93
    ‍♀️
    1.93
    、​
    1.71
    স্ট
    1.70
    त्र
    1.69
    𝐡
    1.66
    lık
    1.66
    ΗΣ
    1.64
    POSITIVE LOGITS
    ه
    1.93
    л
    1.91
     personnaliser
    1.69
    𝗻
    1.61
     unbeatable
    1.58
    𝗿
    1.57
    っと
    1.56
     πάν
    1.55
    د
    1.55
    ство
    1.53
    Act Density 0.213%

    No Known Activations