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
     putting
    0.84
     CNN
    0.82
     bal
    0.80
     tried
    0.79
     malware
    0.79
     developmental
    0.78
     Pokémon
    0.77
     delegation
    0.75
     Santa
    0.74
     Warren
    0.74
    POSITIVE LOGITS
    document
    1.89
    Document
    1.49
     document
    1.46
     документ
    1.42
     documento
    1.36
    DOCUMENT
    1.32
     Document
    1.30
     dokument
    1.29
     документа
    1.21
    doc
    1.18
    Act Density 0.001%

    No Known Activations