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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embeddings
    -0.07
    โลย
    -0.07
    _matches
    -0.07
    .xticks
    -0.07
     formato
    -0.06
     sublist
    -0.06
    Sand
    -0.06
     MAL
    -0.06
    .members
    -0.06
    Longitude
    -0.06
    POSITIVE LOGITS
     uzman
    0.06
      ↵
    0.06
     कट
    0.06
     $$
    0.06
     shaving
    0.06
    ạt
    0.06
    arranty
    0.06
     Там
    0.06
    —they
    0.06
     vivastreet
    0.06
    Act Density 0.003%

    No Known Activations