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

    Neuronpedia

    INDEX
    Explanations

    physical descriptions and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ныя
    0.51
    ницу
    0.49
     olursa
    0.47
     Теле
    0.47
    𒁺
    0.46
    bear
    0.45
    Prim
    0.45
    iguous
    0.45
    이지만
    0.45
    タイル
    0.44
    POSITIVE LOGITS
    o
    0.57
    و
    0.52
     Student
    0.45
     photographic
    0.43
    ो
    0.43
     proclaims
    0.42
     rues
    0.42
     lymphoblastic
    0.41
     phot
    0.41
    asia
    0.41
    Act Density 0.001%

    No Known Activations