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

    Neuronpedia

    INDEX
    Explanations

    namespace declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dris
    0.59
     Err
    0.59
     সিদ্ধান্ত
    0.58
    inding
    0.58
    之类的
    0.56
     থাক
    0.55
     Mow
    0.54
    requis
    0.54
    是不是
    0.54
     kd
    0.53
    POSITIVE LOGITS
    namespace
    1.02
     namespace
    0.94
    namespaces
    0.68
     namespaces
    0.67
     Namespace
    0.67
     nome
    0.66
     ناحيه
    0.65
    nome
    0.64
    Nombre
    0.62
     nomes
    0.61
    Act Density 0.003%

    No Known Activations