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

    Neuronpedia

    INDEX
    Explanations

    museums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    0.56
     μην
    0.50
    Raj
    0.48
    Apparently
    0.46
    wis
    0.44
    Devices
    0.43
    Analog
    0.43
    Unlike
    0.43
    Rows
    0.42
    았다
    0.42
    POSITIVE LOGITS
     relatório
    0.49
    textwidth
    0.46
    શ
    0.45
    ے
    0.44
     μεταξύ
    0.44
     pergunta
    0.44
     Muchas
    0.44
    ায়
    0.43
    en
    0.43
    নমেন্ট
    0.43
    Act Density 0.003%

    No Known Activations