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

    Neuronpedia

    INDEX
    Explanations

    algebraic structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dedos
    0.28
     strat
    0.25
     դ
    0.25
     tuần
    0.24
     অন্ত
    0.23
    äär
    0.23
    belum
    0.23
    strat
    0.23
     creare
    0.22
    それを
    0.22
    POSITIVE LOGITS
    눗
    0.24
     मानदंड
    0.23
     निम्नलिखित
    0.23
     број
    0.23
     등으로
    0.23
    당
    0.23
    щи
    0.23
     Algebraic
    0.22
    Algebra
    0.22
     √
    0.22
    Act Density 0.000%

    No Known Activations