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

    Neuronpedia

    INDEX
    Explanations

    in + year or historical period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     इसमें
    0.27
    इसमें
    0.26
    мір
    0.24
     selles
    0.23
    இதில்
    0.22
     getAll
    0.22
    pInBuffer
    0.22
    InData
    0.21
     उसमें
    0.21
    Num
    0.21
    POSITIVE LOGITS
     a
    0.42
     the
    0.40
     accordance
    0.33
     lieu
    0.33
     an
    0.32
     its
    0.29
     late
    0.29
     Spain
    0.29
     Canada
    0.27
     their
    0.27
    Act Density 0.271%

    No Known Activations