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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "let me" or "let's"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    วิธีการ
    0.69
    为了
    0.67
     Assembl
    0.63
     ():
    0.59
     viscoelastic
    0.58
     Achieving
    0.58
    법
    0.58
    那么
    0.57
     خالص
    0.57
     고급
    0.56
    POSITIVE LOGITS
    ವಹ
    0.70
    áf
    0.67
    ≖
    0.66
    ეხ
    0.63
    uanya
    0.63
     यही
    0.63
    urr
    0.62
     já
    0.62
    нын
    0.60
     agrav
    0.60
    Act Density 0.054%

    No Known Activations