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

    Neuronpedia

    INDEX
    Explanations

    automatic, wireless, commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rather
    0.59
    Į
    0.55
    埓
    0.54
     Mane
    0.53
     Most
    0.52
     Due
    0.52
     personalities
    0.52
     Ð
    0.52
     Among
    0.51
     Regarding
    0.51
    POSITIVE LOGITS
    自动
    0.66
     automáticamente
    0.60
    automatically
    0.59
     otomatis
    0.58
     automático
    0.55
     otomatik
    0.55
    automatic
    0.55
    bluetooth
    0.55
     automática
    0.54
    Seoul
    0.53
    Act Density 0.491%

    No Known Activations