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

    Neuronpedia

    INDEX
    Explanations

    document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    芫
    0.44
    bottlecap
    0.39
    bindingFields
    0.39
    érir
    0.39
    ын
    0.38
    顾客
    0.38
     निपट
    0.38
     tote
    0.37
     اقت
    0.37
    giphy
    0.37
    POSITIVE LOGITS
    document
    0.93
     document
    0.84
    Document
    0.80
     Document
    0.80
     documents
    0.70
     documento
    0.69
     документ
    0.68
     문서
    0.65
     दस्तावेज
    0.64
     dokumen
    0.63
    Act Density 0.000%

    No Known Activations