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

    Neuronpedia

    INDEX
    Explanations

    metabolism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    0.70
     ตัว
    0.58
     on
    0.57
     الرح
    0.56
     عبدالله
    0.55
     الد
    0.55
    ோ
    0.55
    ｶ
    0.55
    ന്ന
    0.54
     أح
    0.53
    POSITIVE LOGITS
    olids
    0.57
     coinvol
    0.55
    u
    0.54
    Ter
    0.54
     workshops
    0.52
    τία
    0.52
     mutations
    0.52
     Workshops
    0.51
     cinemas
    0.50
    ol
    0.50
    Act Density 0.001%

    No Known Activations