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

    Neuronpedia

    INDEX
    Explanations

    their, without, orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aac
    0.22
    anath
    0.21
     ț
    0.21
    なさ
    0.21
     ABV
    0.21
     aastal
    0.21
    kappa
    0.20
    udarstvennyj
    0.20
    ্টা
    0.20
     côtes
    0.20
    POSITIVE LOGITS
    他们的
    0.25
     उनके
    0.25
     Những
    0.25
     χωρίς
    0.24
     Without
    0.24
    Their
    0.24
    That
    0.24
    Without
    0.23
    ☄
    0.23
     реальности
    0.23
    Act Density 0.305%

    No Known Activations