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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parser
    0.39
     pathname
    0.37
    uição
    0.35
    новый
    0.35
     Puma
    0.35
    restart
    0.35
     Calculate
    0.34
     restart
    0.34
     Ak
    0.34
    த்திரம்
    0.34
    POSITIVE LOGITS
    Privacy
    0.39
    ၾ
    0.39
    ട്
    0.38
     договор
    0.38
    แล
    0.37
    Comunic
    0.37
    Hors
    0.37
    做事
    0.37
    кы
    0.37
    чью
    0.36
    Act Density 0.092%

    No Known Activations