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

    Neuronpedia

    INDEX
    Explanations

    joining or options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एक्स
    0.39
     Dard
    0.38
     edilen
    0.37
    如果你
    0.37
     ایف
    0.36
    лянчук
    0.36
    某个
    0.36
    园
    0.35
     if
    0.35
     portrays
    0.34
    POSITIVE LOGITS
     workplaces
    0.43
     सेलेना
    0.41
     workstations
    0.39
    ineuse
    0.39
     progressivement
    0.39
    不斷
    0.39
     insignificant
    0.38
     техно
    0.38
     salles
    0.38
     സഹായി
    0.38
    Act Density 0.001%

    No Known Activations