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

    Neuronpedia

    INDEX
    Explanations

    I've noticed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alas
    0.45
     sections
    0.45
     Ainsi
    0.44
    '!
    0.44
     إليه
    0.44
     입니다
    0.44
     archivos
    0.43
     พร้อม
    0.43
     adlı
    0.43
     algorithms
    0.43
    POSITIVE LOGITS
    Right
    0.44
     Actually
    0.41
    things
    0.41
    भात
    0.41
     Nobody
    0.41
    actually
    0.41
     Right
    0.41
    I
    0.40
     നമ്മ
    0.39
    when
    0.39
    Act Density 0.006%

    No Known Activations