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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    instances
    0.61
     cuerpos
    0.61
     instances
    0.58
    翘
    0.56
    objs
    0.55
    Instances
    0.54
     swipe
    0.53
     निवास
    0.52
     якія
    0.52
     occur
    0.52
    POSITIVE LOGITS
     Dao
    0.61
     UserDao
    0.59
     Andi
    0.56
     বিশেষজ্ঞ
    0.56
     Lauder
    0.55
     David
    0.54
     imaginable
    0.54
     ERISA
    0.54
     ALEXANDER
    0.54
     Bahkan
    0.53
    Act Density 0.001%

    No Known Activations