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

    Neuronpedia

    INDEX
    Explanations

    that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zobac
    0.30
     disappointment
    0.29
    我要
    0.28
    を見
    0.28
     আমাকে
    0.28
    他說
    0.28
     diharapkan
    0.28
    っいて
    0.27
     creencias
    0.27
     ພວກເຮົາ
    0.27
    POSITIVE LOGITS
    。
    0.42
    et
    0.31
    :",
    0.30
    ：
    0.30
     。
    0.29
    ।
    0.29
    ，
    0.29
     една
    0.28
    isola
    0.28
    ut
    0.28
    Act Density 0.030%

    No Known Activations