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

    Neuronpedia

    INDEX
    Explanations

    peace be upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cts
    0.70
     प्राकृतिक
    0.69
    ച
    0.67
    越來越
    0.66
     nominally
    0.66
    ਾਇ
    0.66
    ening
    0.65
    small
    0.64
     immersed
    0.64
     Niro
    0.63
    POSITIVE LOGITS
     Recher
    0.69
     determinar
    0.66
     رفع
    0.66
    を確認
    0.65
     seleccionar
    0.64
     confir
    0.64
    ⊗
    0.62
     auswählen
    0.62
    อื่น
    0.62
     pregunt
    0.62
    Act Density 0.001%

    No Known Activations