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

    Neuronpedia

    INDEX
    Explanations

    same distance, high cohesion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tobacco
    0.52
     venta
    0.46
     auction
    0.46
     venturing
    0.46
     transatlantic
    0.45
     interplanetary
    0.45
     taxation
    0.44
     Tobacco
    0.44
     abbreviation
    0.44
     SPS
    0.44
    POSITIVE LOGITS
    was
    0.49
    Ihr
    0.47
     সংক্রমণ
    0.46
    Pem
    0.46
    didn
    0.45
    졌
    0.43
    ých
    0.43
    ého
    0.42
    ým
    0.42
    owym
    0.42
    Act Density 0.005%

    No Known Activations