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

    Neuronpedia

    INDEX
    Explanations

    possible operator approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обеспечивает
    0.54
     главное
    0.50
     laissent
    0.48
    这是一个
    0.46
    ypeł
    0.46
     trotz
    0.46
     забезпе
    0.45
    '
    0.45
    la
    0.45
     zapewnia
    0.45
    POSITIVE LOGITS
     exclusively
    0.62
     interleukin
    0.55
     published
    0.55
     demethyl
    0.55
     candidacy
    0.54
     benzyl
    0.54
     এবং
    0.54
     iodide
    0.53
     imidazol
    0.53
     fintech
    0.52
    Act Density 0.004%

    No Known Activations