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

    Neuronpedia

    INDEX
    Explanations

    I, she, he, you say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     речь
    0.43
     इसे
    0.42
     इसको
    0.42
     এটাকে
    0.41
     మార
    0.38
     এটিকে
    0.38
    いる
    0.38
    Contains
    0.37
    ಗಳು
    0.37
     इसमें
    0.36
    POSITIVE LOGITS
     deems
    0.63
     deem
    0.61
     deemed
    0.53
     považ
    0.49
    jne
    0.46
     считают
    0.44
     thankfully
    0.43
     dearly
    0.43
    認為
    0.42
    认为是
    0.41
    Act Density 0.037%

    No Known Activations