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

    Neuronpedia

    INDEX
    Explanations

    name identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    名为
    0.44
     الكلام
    0.43
     nas
    0.41
    名叫
    0.38
     nacido
    0.37
    Richmond
    0.36
     اسمه
    0.36
     टिप्पणी
    0.36
     naran
    0.36
    MIL
    0.36
    POSITIVE LOGITS
    plate
    0.82
    करण
    0.80
    plates
    0.76
    clature
    0.68
    geving
    0.68
    akes
    0.64
    કરણ
    0.59
    Surname
    0.59
    まえ
    0.58
    urname
    0.57
    Act Density 0.119%

    No Known Activations